© 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. 25353
    Prev
    Next
    INDEX
    Explanations

    UUIDs and timestamps

    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
     for
    -2.09
     to
    -1.74
     on
    -1.61
     from
    -1.45
     by
    -1.41
     or
    -1.30
     of
    -1.25
     like
    -1.24
     Dezember
    -1.23
     as
    -1.23
    POSITIVE LOGITS
     réinitial
    1.48
    Mí
    1.42
     empêcher
    1.41
    Kval
    1.41
     arrêter
    1.40
     éte
    1.37
    Gön
    1.36
    Nouvelle
    1.34
     bloquer
    1.34
     réessayer
    1.33
    Activations Density 0.002%

    No Known Activations