© 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. 34-GEMMASCOPE-RES-131K
    7. 110547
    Prev
    Next
    INDEX
    Explanations

    capturing beginnings of specific words

    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_34/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
     rosario
    -0.91
     kutoka
    -0.91
     siyang
    -0.86
     nzuri
    -0.83
     εί
    -0.79
     Barrios
    -0.79
    也没有
    -0.78
     vega
    -0.75
    golang
    -0.75
    erli
    -0.75
    POSITIVE LOGITS
     models
    0.84
     alas
    0.83
    Frage
    0.82
    的一切
    0.82
    Modelos
    0.81
     बात
    0.81
    ioni
    0.81
    anken
    0.80
    inkles
    0.79
    )])
    0.79
    Activations Density 0.000%

    No Known Activations