© 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. 22-GEMMASCOPE-RES-131K
    7. 73309
    Prev
    Next
    INDEX
    Explanations

    each subsequent item

    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
    anguages
    -0.94
     either
    -0.89
    playlists
    -0.89
    damente
    -0.88
    ToTensor
    -0.87
    ributors
    -0.87
     invariably
    -0.86
    ｯ
    -0.85
     blessings
    -0.85
     Leute
    -0.85
    POSITIVE LOGITS
     each
    2.91
    each
    1.91
    各
    1.88
     각
    1.84
    各个
    1.81
    Each
    1.72
    每个
    1.71
     poszczegól
    1.68
     Each
    1.66
     chacune
    1.60
    Activations Density 0.165%

    No Known Activations