© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1494
    Prev
    Next
    INDEX
    Explanations

    has been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    -
    1.17
    R
    1.10
    ir
    1.04
    t
    1.04
    r
    1.03
    ib
    1.03
    g
    1.03
    T
    1.03
    er
    1.02
    I
    0.96
    POSITIVE LOGITS
     been
    1.89
     avuto
    1.76
     BEEN
    1.71
     gotten
    1.71
    <unused2165>
    1.68
     været
    1.62
    <unused1127>
    1.60
     fått
    1.58
    <unused2146>
    1.57
     olnud
    1.57
    Activations Density 0.869%

    No Known Activations