© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 93793
    Prev
    Next
    INDEX
    Explanations

    profitability, Agency, understanding

    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
    cane
    0.50
    kan
    0.46
    भा
    0.45
    as
    0.44
    تش
    0.43
     音
    0.43
    _
    0.43
     Mood
    0.42
    ب
    0.42
    ,/
    0.41
    POSITIVE LOGITS
     νέα
    0.45
    ോടെ
    0.44
     avantaj
    0.44
     plow
    0.44
     점에서
    0.43
     telecom
    0.43
    갤럭
    0.43
    ниць
    0.41
     ventaja
    0.41
    પતિ
    0.41
    Activations Density 0.009%

    No Known Activations