© 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. 1391
    Prev
    Next
    INDEX
    Explanations

    spells out calculation

    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
     partners
    0.51
     Gord
    0.49
     Ign
    0.48
    ﮐ
    0.47
     coordinate
    0.47
     discrepancies
    0.46
     Jov
    0.45
     conversions
    0.45
     Lewis
    0.45
     dissolved
    0.45
    POSITIVE LOGITS
    ｎ
    0.48
    ్యాచ్
    0.47
     አይደለም
    0.47
    不但
    0.47
    𝐞
    0.47
     薄
    0.46
    raving
    0.46
     تعدى
    0.46
     latéraux
    0.45
    不仅
    0.45
    Activations Density 0.000%

    No Known Activations