© 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. 15257
    Prev
    Next
    INDEX
    Explanations

    package info

    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
     if
    -1.30
     jeśli
    -1.23
    ırl
    -1.19
     évé
    -1.17
     Espíritu
    -1.13
     how
    -1.12
     начин
    -1.10
     Capitán
    -1.09
    UBLIC
    -1.06
     Sơ
    -1.04
    POSITIVE LOGITS
    aspectj
    1.07
     ativar
    1.05
    引起了
    1.00
     району
    0.99
     lecciones
    0.99
    ጴ
    0.99
     semelhante
    0.98
     plupart
    0.98
    了不少
    0.98
     Hinsicht
    0.98
    Activations Density 0.000%

    No Known Activations