© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58753
    Prev
    Next
    INDEX
    Explanations

    code identifiers and comments

    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
    配套
    -0.80
    rawtypes
    -0.79
    Rv
    -0.77
     problems
    -0.75
     unethical
    -0.73
    ValueChanged
    -0.73
     walked
    -0.73
     Since
    -0.72
     Publicity
    -0.71
     Sech
    -0.71
    POSITIVE LOGITS
    machine
    0.88
     machine
    0.85
     svě
    0.84
    ruz
    0.84
     adultes
    0.79
     FDR
    0.77
    ʻ
    0.77
    innerText
    0.77
     MICRO
    0.77
    dried
    0.76
    Activations Density 0.005%

    No Known Activations