© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6910
    Prev
    Next
    INDEX
    Explanations

    code, modifiers, objects

    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
     one
    -1.58
     in
    -1.52
     even
    -1.45
     Even
    -1.34
     not
    -1.34
     Usually
    -1.28
     While
    -1.28
     an
    -1.27
     Though
    -1.27
     it
    -1.25
    POSITIVE LOGITS
     herunter
    1.23
     verminder
    1.19
     ayur
    1.16
    瞇
    1.13
     TRUTH
    1.09
    tav
    1.05
    噘
    1.04
     ſol
    1.03
     BEAUTIFUL
    1.03
     ROBERT
    1.02
    Activations Density 0.001%

    No Known Activations