© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66508
    Prev
    Next
    INDEX
    Explanations

    University, Institute, Carbon, Hel, //

    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_22/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
    泐
    -1.54
    voyez
    -1.51
     jednod
    -1.51
     soñar
    -1.51
    鮡
    -1.49
     calzado
    -1.48
    Ꮴ
    -1.47
     refroid
    -1.45
     Diſ
    -1.44
     coûte
    -1.43
    POSITIVE LOGITS
     also
    1.84
    u
    1.75
    f
    1.71
    N
    1.69
    n
    1.69
    P
    1.69
    g
    1.67
    d
    1.66
    M
    1.64
    is
    1.63
    Activations Density 0.000%

    No Known Activations