© 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. 13324
    Prev
    Next
    INDEX
    Explanations

    separators and equations

    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
    hin
    0.39
    वे
    0.39
    성에
    0.38
    हांत
    0.38
    력
    0.36
     vectorial
    0.36
    ή
    0.36
    haven
    0.36
    crack
    0.35
    strength
    0.35
    POSITIVE LOGITS
     separator
    0.40
     Meade
    0.37
     separators
    0.37
    ଡ
    0.37
     floats
    0.37
    jesi
    0.36
    排放
    0.36
     checkpoints
    0.36
    ǧ
    0.35
    Predicate
    0.35
    Activations Density 0.003%

    No Known Activations