© 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. 158085
    Prev
    Next
    INDEX
    Explanations

    Names followed by actions

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

    names and their reactions

    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
     замети
    0.48
     مت
    0.48
     خط
    0.47
     سريع
    0.46
     remarquer
    0.45
    rezent
    0.44
     ਟ
    0.43
     habían
    0.43
    arrera
    0.43
     замет
    0.43
    POSITIVE LOGITS
     помогает
    0.45
    ৱ
    0.43
    এটা
    0.41
     borrows
    0.40
    Está
    0.40
     এসেছি
    0.40
    ᵒ
    0.39
    *
    0.39
     is
    0.39
     isn
    0.39
    Activations Density 0.001%

    No Known Activations