© 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. 63277
    Prev
    Next
    INDEX
    Explanations

    F- prefix

    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
     perhaps
    -1.29
     Perhaps
    -1.14
     both
    -1.08
     any
    -1.05
    est
    -0.93
     taking
    -0.92
     within
    -0.90
     not
    -0.88
    上げた
    -0.87
    等着
    -0.87
    POSITIVE LOGITS
    xF
    0.96
    structors
    0.94
     favori
    0.94
     F
    0.94
     périodes
    0.93
     flink
    0.93
     formid
    0.92
    sipasi
    0.92
     JAY
    0.91
    Arial
    0.91
    Activations Density 0.128%

    No Known Activations