© 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. 12777
    Prev
    Next
    INDEX
    Explanations

    compare or contrast

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

    breakdown of explanations

    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_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
     TRPV
    0.47
     incluso
    0.44
     पाच
    0.41
     ď
    0.41
     સંપૂર્ણ
    0.40
     strikingly
    0.40
     unanticipated
    0.40
    鈽
    0.40
     vše
    0.39
     केन्द्रीय
    0.39
    POSITIVE LOGITS
    /
    0.55
     কিংবা
    0.40
    /"
    0.37
    或者
    0.37
    明确
    0.36
    或者是
    0.36
    :
    0.35
    我对
    0.35
    or
    0.35
    ahaman
    0.35
    Activations Density 0.259%

    No Known Activations