© 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. 11563
    Prev
    Next
    INDEX
    Explanations

    DOI and citations

    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
     egens
    -1.10
     rekke
    -1.04
     forfatter
    -1.02
     conozco
    -1.02
    tempts
    -0.99
     chaleco
    -0.99
     Chúa
    -0.99
     entiendo
    -0.99
     dosta
    -0.97
    '},
    -0.97
    POSITIVE LOGITS
     and
    1.16
     with
    1.10
    Legende
    0.98
     nuestras
    0.96
     our
    0.96
     vs
    0.95
     oluşan
    0.93
    conector
    0.93
    clases
    0.91
     günlük
    0.90
    Activations Density 0.005%

    No Known Activations