© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9512
    Prev
    Next
    INDEX
    Explanations

    code context and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
     పో
    0.66
     haciendo
    0.64
    btc
    0.64
     ڈ
    0.63
     ಡ
    0.60
     পৌ
    0.57
     বলো
    0.57
     abaste
    0.56
     ਡ
    0.55
     ingeniero
    0.55
    POSITIVE LOGITS
    typical
    0.58
    为止
    0.58
    usually
    0.55
    นิยม
    0.54
    通常
    0.54
    中間
    0.54
     typical
    0.53
    が生
    0.52
    typically
    0.52
     #'
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.