© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32607
    Prev
    Next
    INDEX
    Explanations

    unspecified or unknown things

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    anii
    -1.10
    IMIN
    -1.08
    urface
    -1.05
    HMAC
    -1.03
     créé
    -1.03
    richtet
    -1.02
     pourront
    -1.02
     traité
    -1.02
     obé
    -0.99
    AHUL
    -0.98
    POSITIVE LOGITS
     that
    2.03
     other
    1.96
     those
    1.48
     what
    1.48
     whatever
    1.43
     when
    1.39
     now
    1.38
     there
    1.32
     still
    1.30
     decided
    1.25
    Activations Density 0.021%

    No Known Activations