© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71465
    Prev
    Next
    INDEX
    Explanations

    psychedelic music and groovy cartoons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </sub>
    -2.17
    er
    -1.98
    le
    -1.92
     that
    -1.90
    ۔
    -1.85
     -
    -1.81
     who
    -1.80
    -1.79
     cual
    -1.77
    􀂃
    -1.76
    POSITIVE LOGITS
    沨
    2.41
    сение
    1.91
    ’
    1.88
    퐸
    1.88
     Belum
    1.85
    搋
    1.84
     Männern
    1.84
    畵
    1.80
    kadang
    1.77
     singuli
    1.77
    Activations Density 0.004%

    No Known Activations