© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67387
    Prev
    Next
    INDEX
    Explanations

    css color properties

    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
     oublier
    -1.33
    鮡
    -1.15
     trouver
    -1.09
    particularly
    -1.04
     miſ
    -1.03
    λικ
    -1.02
     cadeaux
    -1.00
     astu
    -1.00
     abonnement
    -1.00
     vendeur
    -0.98
    POSITIVE LOGITS
     from
    1.18
     increased
    1.16
     more
    1.10
     at
    1.08
     with
    1.07
     or
    1.03
     and
    1.02
     slightly
    1.00
     came
    1.00
     during
    1.00
    Activations Density 0.005%

    No Known Activations