© 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. 22-GEMMASCOPE-RES-131K
    7. 65468
    Prev
    Next
    INDEX
    Explanations

    licenses and disclaimers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     longterm
    -1.30
     verschillende
    -1.30
     decoracion
    -1.24
     =
    -1.23
     prachtige
    -1.19
     sabid
    -1.16
     \
    -1.13
     satılık
    -1.12
     Niños
    -1.10
     grève
    -1.10
    POSITIVE LOGITS
     Since
    1.21
     To
    1.17
     Perhaps
    1.15
     C
    1.15
     by
    1.11
     can
    1.09
     Even
    1.08
    olkata
    1.07
     In
    1.07
     Both
    1.06
    Activations Density 0.323%

    No Known Activations