© 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. 65271
    Prev
    Next
    INDEX
    Explanations

    question or introduction labels

    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
    enseignements
    -1.23
     there
    -1.22
     to
    -1.16
    <blockquote>
    -1.16
    édie
    -1.10
    〜。
    -1.10
     饰
    -1.07
    諍
    -1.07
    論
    -1.05
    streets
    -1.05
    POSITIVE LOGITS
     consommer
    1.20
     nourrir
    1.20
     fabriquer
    1.16
    INGRED
    1.16
    粍
    1.14
     nettoyer
    1.10
    ￪
    1.09
     mittler
    1.09
    organised
    1.08
    Och
    1.07
    Activations Density 0.000%

    No Known Activations