© 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. 34-GEMMASCOPE-RES-131K
    7. 87298
    Prev
    Next
    INDEX
    Explanations

    starts of specific names or terms

    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_34/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
     sortBy
    -0.84
    pulos
    -0.71
    ืม
    -0.71
    what
    -0.69
    ?_
    -0.69
    Lời
    -0.68
     fratelli
    -0.67
    ल्ड
    -0.66
    président
    -0.66
     拼
    -0.66
    POSITIVE LOGITS
    ennifer
    0.81
    Mako
    0.80
     compañ
    0.79
     cipher
    0.78
    uline
    0.77
    Micha
    0.77
    corruption
    0.77
     marki
    0.77
    deniz
    0.75
    Eb
    0.75
    Activations Density 0.000%

    No Known Activations