© 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. 128638
    Prev
    Next
    INDEX
    Explanations

    modelA total, Q:, Vehicles require

    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
     évé
    -1.21
    🤑
    -1.12
     (
    -1.05
     from
    -1.04
     Often
    -1.03
     oktober
    -1.02
     erd
    -1.02
     foton
    -1.01
     tiro
    -1.01
     Before
    -1.01
    POSITIVE LOGITS
    oiseau
    1.25
     регионе
    1.23
    Continu
    1.23
    
    1.17
    geleitet
    1.13
     ayudan
    1.12
    忤
    1.12
    ennemi
    1.09
    щность
    1.09
    Largeur
    1.08
    Activations Density 0.001%

    No Known Activations