© 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. 17-GEMMASCOPE-2-RES-16K
    7. 180
    Prev
    Next
    INDEX
    Explanations

    you could tell me

    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_17_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
    ,
    2.07
    ،
    1.79
    :
    1.49
    、
    1.48
    -
    1.47
    .
    1.34
    ِ
    1.33
    )،
    1.32
    ;
    1.31
    /
    1.30
    POSITIVE LOGITS
     they
    3.11
     we
    3.04
     there
    2.99
     it
    2.74
     you
    2.42
    they
    2.32
    there
    2.30
     THEY
    2.12
     они
    2.11
     she
    2.04
    Activations Density 1.850%

    No Known Activations