© 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. 59591
    Prev
    Next
    INDEX
    Explanations

    release notes and publication dates

    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
    Scaler
    -0.79
     fertiliz
    -0.78
     fertilization
    -0.74
    randint
    -0.73
    Referências
    -0.73
    acterium
    -0.71
     exemplar
    -0.71
     lander
    -0.69
    Soft
    -0.69
    Contracts
    -0.68
    POSITIVE LOGITS
     geschlagen
    0.78
    CPT
    0.77
     F
    0.77
    OGRAPH
    0.75
    ఔ
    0.74
     czerwony
    0.74
     floss
    0.73
    она
    0.72
    miso
    0.72
     conjunta
    0.72
    Activations Density 0.001%

    No Known Activations