© 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. 25884
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
     publier
    -1.09
     réserver
    -0.99
     écouter
    -0.97
     astuces
    -0.95
     dépenses
    -0.95
     unités
    -0.94
     arrêter
    -0.94
     mouvements
    -0.93
     méthodes
    -0.92
     détruire
    -0.92
    POSITIVE LOGITS
     their
    1.13
     one
    1.12
     any
    1.06
     including
    1.04
     ensuring
    1.03
     took
    1.02
     wants
    1.02
     Often
    0.98
     could
    0.98
     which
    0.98
    Activations Density 0.020%

    No Known Activations