© 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. 11434
    Prev
    Next
    INDEX
    Explanations

    text separators and punctuation

    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
    ρίου
    -1.07
     chỉ
    -0.98
     during
    -0.85
    since
    -0.85
     "
    -0.84
     Very
    -0.83
    声が
    -0.82
    dientemente
    -0.81
    naby
    -0.81
    REA
    -0.81
    POSITIVE LOGITS
    ={({
    0.89
    牴
    0.85
    spans
    0.84
     PRODUCTO
    0.82
    永遠
    0.81
     Preparatory
    0.80
    ₚ
    0.79
     PREPAR
    0.79
    }{#
    0.77
     Wildcard
    0.77
    Activations Density 0.001%

    No Known Activations