© 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. 10-GEMMASCOPE-RES-131K
    7. 59556
    Prev
    Next
    INDEX
    Explanations

    android imports

    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_10/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
    鶺
    -1.42
     Tamaño
    -1.33
     tunik
    -1.31
     that
    -1.30
    ってない
    -1.30
    っていない
    -1.27
     sandalias
    -1.25
     reklama
    -1.24
     Infór
    -1.23
     Якщо
    -1.23
    POSITIVE LOGITS
     with
    1.23
    cension
    1.11
     sur
    1.11
    ський
    1.09
     see
    1.08
     although
    1.05
    talet
    1.05
     tried
    1.05
     to
    1.04
     find
    1.04
    Activations Density 0.058%

    No Known Activations