© 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. 78835
    Prev
    Next
    INDEX
    Explanations

    Narasimha, devotee, Hatha

    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
     adverse
    -0.87
     Democratic
    -0.83
    xos
    -0.79
     anticipated
    -0.78
     פ
    -0.78
     specimens
    -0.76
    Toolkit
    -0.76
     PGA
    -0.75
    cobs
    -0.75
     Kennedy
    -0.73
    POSITIVE LOGITS
     Isk
    0.88
     Fundraising
    0.84
     homeschool
    0.80
     devotee
    0.79
     isk
    0.76
     Vr
    0.75
    ISK
    0.74
     システム
    0.73
    Ха
    0.73
    fundo
    0.71
    Activations Density 0.009%

    No Known Activations