© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49289
    Prev
    Next
    INDEX
    Explanations

    short circuit or working again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *
    0.46
     наиболее
    0.45
     материала
    0.43
    mate
    0.42
     попада
    0.42
    rukt
    0.42
     эпи
    0.42
     избе
    0.42
    try
    0.42
    क्रामक
    0.42
    POSITIVE LOGITS
     Calyce
    0.49
     momentary
    0.46
     momentarily
    0.46
     périphérique
    0.46
     signified
    0.43
    踴
    0.43
     पंडित
    0.43
     ልዩ
    0.42
    աջ
    0.42
    胥
    0.42
    Activations Density 0.010%

    No Known Activations