© 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-262K
    7. 194945
    Prev
    Next
    INDEX
    Explanations

    ready to

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

    extracting greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     է
    0.53
    ται
    0.49
     monaster
    0.48
     умолча
    0.48
     cuir
    0.47
     Сою
    0.46
    銃
    0.46
    ስ
    0.46
    こだわり
    0.44
    क्ष्म
    0.44
    POSITIVE LOGITS
    ibol
    0.52
    ierte
    0.49
    Sci
    0.49
    hemi
    0.49
    avin
    0.48
    asak
    0.47
    metics
    0.46
    Han
    0.46
     কার্যত
    0.46
    WART
    0.45
    Activations Density 0.001%

    No Known Activations