© 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. 63673
    Prev
    Next
    INDEX
    Explanations

    at a descriptor

    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
     laude
    -0.95
     مسلمان
    -0.90
    mixins
    -0.88
    达到了
    -0.88
     ranged
    -0.86
     Metacritic
    -0.86
     amount
    -0.85
     dolce
    -0.85
    sized
    -0.85
     tipis
    -0.84
    POSITIVE LOGITS
     around
    1.02
     a
    0.94
     angene
    0.93
     arasındaki
    0.93
     около
    0.93
     mengumpulkan
    0.92
     what
    0.88
     near
    0.85
     full
    0.82
     kolem
    0.81
    Activations Density 0.082%

    No Known Activations