© 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. 57221
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

    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
     Fed
    -0.70
     Holden
    -0.68
     impeach
    -0.66
     BaseController
    -0.65
     Foote
    -0.64
     Foot
    -0.63
     Bengaluru
    -0.63
     GameManager
    -0.63
    IdList
    -0.63
     WTO
    -0.62
    POSITIVE LOGITS
    icen
    0.73
    른
    0.68
    álogos
    0.68
    ஷ
    0.67
    Barcode
    0.66
     spars
    0.66
    winner
    0.66
    Winner
    0.66
    opathie
    0.66
    roxene
    0.64
    Activations Density 0.044%

    No Known Activations