© 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. 33158
    Prev
    Next
    INDEX
    Explanations

    list elements and values

    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
     or
    -1.48
     also
    -1.30
     had
    -1.21
     continued
    -1.18
     was
    -1.18
     will
    -1.16
     added
    -1.13
     could
    -1.12
     probably
    -1.09
     still
    -1.07
    POSITIVE LOGITS
     konsumen
    1.11
     ekolog
    1.10
     esetén
    1.04
     abstrak
    1.04
     всички
    1.02
     katalog
    1.02
     obiet
    1.01
     prennent
    1.00
     ceremonia
    1.00
     contenir
    1.00
    Activations Density 0.022%

    No Known Activations