© 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
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2789
    Prev
    Next
    INDEX
    Explanations

    practical blueprint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    :
    1.46
     :
    0.99
    :[
    0.89
    :.
    0.84
    :&
    0.83
    :-
    0.83
    :");
    0.81
    :}
    0.79
     :-
    0.79
    :</
    0.79
    POSITIVE LOGITS
    <unused1083>
    1.30
    <unused1852>
    1.26
    Ꭽ
    1.18
    <unused1138>
    1.17
    <unused717>
    1.16
    Ꭳ
    1.15
     رغم
    1.15
    ଧ
    1.15
     любов
    1.15
    牷
    1.15
    Activations Density 0.020%

    No Known Activations