© 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. 123567
    Prev
    Next
    INDEX
    Explanations

    specialized terminology and contexts

    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
    тоў
    0.52
    и
    0.50
    浥
    0.47
    ח
    0.46
    I
    0.45
    ப்படு
    0.45
    ев
    0.45
    декс
    0.44
     جائزہ
    0.44
    п
    0.44
    POSITIVE LOGITS
     vendre
    0.47
     unseren
    0.46
     dbo
    0.46
     trei
    0.45
     deinen
    0.45
     meinen
    0.45
     vele
    0.44
     starboard
    0.44
     東京都
    0.43
     Putra
    0.42
    Activations Density 0.001%

    No Known Activations