© 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-262K
    7. 123419
    Prev
    Next
    INDEX
    Explanations

    specific requests or details

    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_262k_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
    槎
    0.48
     vấn
    0.47
     алюми
    0.47
    愤
    0.46
    on
    0.43
     ചെയ
    0.43
    ம
    0.43
    टो
    0.43
    पो
    0.42
    ಆ
    0.42
    POSITIVE LOGITS
     agricultura
    0.51
    sock
    0.43
    Mailer
    0.42
    neighbor
    0.42
    кой
    0.42
     abundante
    0.41
     física
    0.41
    hotite
    0.40
    stripos
    0.39
     nerada
    0.39
    Activations Density 0.004%

    No Known Activations