© 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. 58040
    Prev
    Next
    INDEX
    Explanations

    event, component, store

    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
    ULUS
    -0.78
    appearing
    -0.71
     Hodgkin
    -0.69
    warran
    -0.68
     کودک
    -0.67
    gensen
    -0.66
    Covered
    -0.65
    ⅴ
    -0.65
    iring
    -0.65
    hirkan
    -0.65
    POSITIVE LOGITS
     ICO
    0.69
     divisions
    0.69
     Justice
    0.68
    擢
    0.67
     suede
    0.66
     urea
    0.65
    啄
    0.64
     SARS
    0.64
    fsch
    0.64
     Fay
    0.63
    Activations Density 0.098%

    No Known Activations