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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 889
    Prev
    Next
    INDEX
    Explanations

    ethical research practices

    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
    2.48
    -
    1.94
    .
    1.90
    ,
    1.81
     in
    1.75
     to
    1.69
    and
    1.68
     or
    1.65
     at
    1.64
    att
    1.63
    POSITIVE LOGITS
     trataro
    3.87
     ObjectTemp
    3.84
    𒀖
    3.81
    𒀠
    3.80
    𒈣
    3.80
    <unused1324>
    3.80
    <unused1316>
    3.79
     ہُما
    3.79
    𒄖
    3.79
     BusABC
    3.78
    Activations Density 0.626%

    No Known Activations