© 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. 34-GEMMASCOPE-RES-131K
    7. 31653
    Prev
    Next
    INDEX
    Explanations

    oracle ADF project identifier

    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
    触摸
    -0.77
     Ozone
    -0.77
    Ozone
    -0.73
     angst
    -0.73
     тай
    -0.73
     Intelli
    -0.72
    сан
    -0.72
    𝐨
    -0.71
     Comune
    -0.71
    lacement
    -0.70
    POSITIVE LOGITS
     ADF
    1.08
    ADF
    0.94
    adf
    0.90
    oracle
    0.88
     oracle
    0.85
    Binding
    0.79
     LOV
    0.79
    Als
    0.77
    invoke
    0.77
     binding
    0.74
    Activations Density 0.017%

    No Known Activations