© 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. 38922
    Prev
    Next
    INDEX
    Explanations

    specific acronyms

    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
     этого
    -1.10
     gets
    -1.07
     demuestra
    -1.04
     just
    -1.04
     demostrar
    -1.03
     femminile
    -1.03
     全新
    -1.03
     Gesund
    -1.02
     this
    -1.01
    guei
    -1.01
    POSITIVE LOGITS
    Przyp
    1.04
    ortic
    1.01
     andra
    0.99
    vably
    0.99
     waking
    0.98
    VE
    0.97
    jercicios
    0.97
    ҫ
    0.96
    istisch
    0.96
    FontOfSize
    0.96
    Activations Density 0.335%

    No Known Activations