© 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. 108175
    Prev
    Next
    INDEX
    Explanations

    safety, estimation, code blocks

    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
    Beginning
    0.53
    Wed
    0.46
    將
    0.44
    Mountains
    0.43
     Beginning
    0.42
    itism
    0.42
    يت
    0.42
    ოვანი
    0.42
    Eight
    0.42
    న్య
    0.41
    POSITIVE LOGITS
     caps
    0.48
     mezzanine
    0.47
     बल
    0.47
    >?
    0.47
     window
    0.47
     recorr
    0.46
     फसल
    0.46
     pel
    0.45
     cob
    0.45
     exatamente
    0.45
    Activations Density 0.000%

    No Known Activations