© 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. 33757
    Prev
    Next
    INDEX
    Explanations

    progress bar or loader

    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
     impromptu
    -1.51
    『
    -1.45
     famed
    -1.44
    ↵
    -1.36
     \&
    -1.34
     flamboyant
    -1.34
     Ensuring
    -1.32
     to
    -1.30
     Bemerkungen
    -1.29
    to
    -1.28
    POSITIVE LOGITS
     porcent
    1.65
     novelas
    1.65
    ación
    1.59
     analis
    1.51
    鱨
    1.49
     vinos
    1.46
    　→
    1.45
     neum
    1.43
     ciber
    1.39
     anivers
    1.38
    Activations Density 0.007%

    No Known Activations