© 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. 76100
    Prev
    Next
    INDEX
    Explanations

    principal component analysis

    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
     Bass
    -0.76
    gos
    -0.73
     elevation
    -0.70
    euvres
    -0.69
     goes
    -0.69
    Scalar
    -0.69
    cdc
    -0.67
    wanie
    -0.66
     なっ
    -0.66
    CDC
    -0.66
    POSITIVE LOGITS
    /¯
    0.67
    PUESTA
    0.67
    REGUL
    0.66
     tagħ
    0.64
    eniging
    0.64
     کلیک
    0.63
     Langdon
    0.63
     vodi
    0.61
     Winding
    0.60
     Zero
    0.60
    Activations Density 0.076%

    No Known Activations