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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11951
    Prev
    Next
    INDEX
    Explanations

    'you'd need'

    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_7_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
     and
    1.34
    ,
    1.20
    .
    1.13
     in
    1.09
    -
    1.08
     with
    1.01
     general
    0.96
    ;
    0.96
    0.91
     I
    0.90
    POSITIVE LOGITS
    𒈪
    2.00
     trataro
    1.99
    
    1.98
    𐰖
    1.93
    <unused1339>
    1.93
    <unused831>
    1.93
     मानबी
    1.92
     nCharString
    1.92
     ObjectTemp
    1.92
     BusABC
    1.91
    Activations Density 0.000%

    No Known Activations