© 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-16K
    7. 593
    Prev
    Next
    INDEX
    Explanations

    been followed by state or happening

    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_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
    the
    1.20
    nya
    1.13
    mid
    1.11
    ll
    1.06
    了
    1.06
    not
    1.06
    maal
    1.06
    ёл
    1.05
    [/
    1.04
    ument
    1.04
    POSITIVE LOGITS
     htonl
    1.73
    ੋਰ
    1.67
    SearchCV
    1.62
    놋
    1.62
    DefinitionGroup
    1.61
    }$&
    1.58
    chyné
    1.57
     columnspan
    1.56
    ৃতা
    1.53
     khử
    1.53
    Activations Density 1.030%

    No Known Activations