© 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. 12376
    Prev
    Next
    INDEX
    Explanations

    Category definitions

    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
     betrek
    -0.93
    ་བ
    -0.91
     respectivamente
    -0.90
     descubierto
    -0.84
    いった
    -0.83
    bmatrix
    -0.82
    ibilità
    -0.82
    PACK
    -0.81
    ⍨
    -0.81
    வெ
    -0.79
    POSITIVE LOGITS
    üe
    0.79
     drame
    0.79
    CONDITIONS
    0.75
     appellants
    0.75
     bero
    0.74
    によっては
    0.73
     пти
    0.72
    侷
    0.72
     favourite
    0.72
     favorito
    0.72
    Activations Density 0.044%

    No Known Activations