© 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. 109927
    Prev
    Next
    INDEX
    Explanations

    string conversion and manipulation

    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
     tầm
    -0.82
     목록
    -0.73
    觉得自己
    -0.72
    動物園
    -0.70
     andar
    -0.69
    いかない
    -0.69
    zete
    -0.69
     Resid
    -0.68
    Decorated
    -0.68
     presso
    -0.68
    POSITIVE LOGITS
     "".
    1.95
     ''.
    1.87
    "".
    1.70
    ''.
    1.55
     ".
    1.37
    ».
    1.27
     '.
    1.26
    ”.
    1.23
    ".
    1.22
    “.
    1.20
    Activations Density 0.022%

    No Known Activations