© 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. 34442
    Prev
    Next
    INDEX
    Explanations

    This is a descriptor

    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
     it
    -1.34
     ansiedad
    -1.16
     funkcji
    -1.16
     sillas
    -1.13
     военной
    -1.13
     latter
    -1.10
     mân
    -1.10
     others
    -1.09
     other
    -1.08
     there
    -1.07
    POSITIVE LOGITS
     This
    1.25
     для
    1.18
     solides
    1.14
     repens
    1.12
     minuten
    1.10
    ным
    1.09
     vogel
    1.09
    関連リンク
    1.06
     tässä
    1.06
     это
    1.05
    Activations Density 0.206%

    No Known Activations