© 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. 146053
    Prev
    Next
    INDEX
    Explanations

    countries, gold, conspiracy

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

    actions and history

    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
    пиона
    0.47
    ंबर
    0.45
    u
    0.45
    also
    0.44
    ir
    0.43
    H
    0.43
    9
    0.42
    new
    0.41
    if
    0.41
    originals
    0.41
    POSITIVE LOGITS
     fasse
    0.49
     Zijn
    0.47
     débat
    0.46
     কথায়
    0.46
     terrasse
    0.45
    讓他
    0.44
     godzin
    0.44
     ശക്ത
    0.44
    فيد
    0.43
    誑
    0.43
    Activations Density 0.000%

    No Known Activations