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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12254
    Prev
    Next
    INDEX
    Explanations

    states and their functioning

    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
     rafra
    -1.83
     maî
    -1.70
     perpé
    -1.66
     Detalles
    -1.66
     siè
    -1.64
     ajouter
    -1.59
     hés
    -1.59
    訁
    -1.58
     éte
    -1.56
     célè
    -1.55
    POSITIVE LOGITS
     not
    2.06
     at
    2.05
     or
    1.99
     what
    1.85
     like
    1.51
     also
    1.50
     where
    1.50
     best
    1.49
     as
    1.48
    !!!!
    1.41
    Activations Density 0.028%

    No Known Activations