© 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. 2611
    Prev
    Next
    INDEX
    Explanations

    instructions and steps

    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
    ∑</
    1.36
    又は
    1.26
    ദ്ധ
    1.25
    ホイール
    1.24
    または
    1.22
    フロ
    1.14
    直
    1.10
     direttamente
    1.09
    ForAll
    1.09
     fürs
    1.08
    POSITIVE LOGITS
    .
    1.64
    :
    1.43
    .:
    1.36
    ;
    1.31
    :-
    1.20
    ,:
    1.19
    ,
    1.18
    。
    1.15
    ..
    1.12
    ?
    1.12
    Activations Density 0.237%

    No Known Activations