© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12671
    Prev
    Next
    INDEX
    Explanations

    end of sentence

    np_acts-logits-general · gemini-2.5-flash-lite

    possessive pronouns or foreign equivalents

    np_acts-logits-general · gemini-2.5-flash-lite

    contemporary trends and change

    np_max-act · claude-4-5-sonnetTriggered by @sk5695

    sentence endings

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     जेव्हा
    0.53
     ट्रिक
    0.45
     பொதுவாக
    0.45
     longtemps
    0.44
     식으로
    0.44
     Generally
    0.44
     उल्लेखनीय
    0.44
     generally
    0.43
    後來
    0.43
     postwar
    0.42
    POSITIVE LOGITS
     તમારા
    0.51
    స్తున్నారు
    0.50
    స్తున్నాయి
    0.50
     culminated
    0.49
     চলছে
    0.47
     amenazas
    0.47
     amenaza
    0.47
    你应该
    0.46
    াচ্ছে
    0.46
     سیاسی
    0.46
    Activations Density 0.233%

    No Known Activations