© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116117
    Prev
    Next
    INDEX
    Explanations

    legal code and licenses

    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
    Saj
    -0.75
    LABOR
    -0.75
    HttpException
    -0.73
     Requiem
    -0.72
    Pays
    -0.71
     YAP
    -0.69
     TIP
    -0.68
    Reb
    -0.68
     야
    -0.67
     mcqueen
    -0.67
    POSITIVE LOGITS
     Montag
    0.72
     lire
    0.70
    encodeWith
    0.70
     giản
    0.68
    county
    0.68
    contador
    0.64
     entre
    0.63
    面の
    0.63
    functional
    0.62
    ე
    0.62
    Activations Density 0.042%

    No Known Activations