© 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. 57402
    Prev
    Next
    INDEX
    Explanations

    scale =

    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
     October
    -1.00
    ffeine
    -0.96
     July
    -0.91
    October
    -0.87
    ideae
    -0.84
    <blockquote>
    -0.84
     what
    -0.83
     Käufer
    -0.83
     November
    -0.82
    assertIs
    -0.82
    POSITIVE LOGITS
    Calend
    1.00
    ☐
    0.97
     ficción
    0.97
    =
    0.96
     ongel
    0.95
     dage
    0.93
    Scales
    0.91
    fores
    0.90
    Espa
    0.89
    masque
    0.88
    Activations Density 0.004%

    No Known Activations