© 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. 84253
    Prev
    Next
    INDEX
    Explanations

    forgetting about

    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
     każdy
    -2.23
    都已经
    -2.11
     rivista
    -1.97
     speranza
    -1.92
     BECAUSE
    -1.91
     verità
    -1.87
     prossima
    -1.85
    壜
    -1.80
     registrazione
    -1.80
     lettura
    -1.79
    POSITIVE LOGITS
    d
    2.13
    '
    1.95
    -
    1.87
    ",
    1.65
    p
    1.62
     or
    1.56
     and
    1.56
     élevés
    1.53
    f
    1.52
    \{
    1.50
    Activations Density 0.001%

    No Known Activations