© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84259
    Prev
    Next
    INDEX
    Explanations

    web sites and files

    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
     Behind
    -0.73
    ynn
    -0.70
     díl
    -0.68
     Arteta
    -0.65
     backend
    -0.65
    Behind
    -0.64
    ेज
    -0.63
    髭
    -0.62
     grow
    -0.62
    료
    -0.61
    POSITIVE LOGITS
     Bous
    0.74
     nonce
    0.69
    ektiv
    0.68
     FSH
    0.67
    rosi
    0.67
    拉
    0.66
     Moreira
    0.64
    bish
    0.63
    ushu
    0.63
     onely
    0.63
    Activations Density 0.085%

    No Known Activations