© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13746
    Prev
    Next
    INDEX
    Explanations

    multi-head attention

    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
    кт
    1.67
    ner
    1.63
    تف
    1.49
    当た
    1.39
    নের
    1.36
    らし
    1.33
    說
    1.32
    نسان
    1.31
    docker
    1.31
    <code>
    1.31
    POSITIVE LOGITS
    ndash
    1.76
     SONG
    1.70
     Coal
    1.68
     ensuing
    1.67
     disadvantages
    1.66
     RCC
    1.64
     Stories
    1.64
     weaknesses
    1.63
    Warnings
    1.62
    蘼
    1.62
    Activations Density 0.000%

    No Known Activations