© 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. 11551
    Prev
    Next
    INDEX
    Explanations

    lists of items or specifications

    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
    knowledge
    -0.92
     Gonzales
    -0.86
     conoscenza
    -0.84
    他にも
    -0.84
    edoria
    -0.82
     renk
    -0.82
    optim
    -0.81
     knowledge
    -0.81
     Bretaña
    -0.80
    顷
    -0.80
    POSITIVE LOGITS
     advierte
    0.98
     nyky
    0.93
    𖥻
    0.83
    nalité
    0.83
     Schichten
    0.77
    ungalow
    0.76
     stellte
    0.75
     häls
    0.75
    cirq
    0.74
     comenzará
    0.74
    Activations Density 0.117%

    No Known Activations