© 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. 143987
    Prev
    Next
    INDEX
    Explanations

    making progress

    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
    attuale
    0.53
     ಅರ್
    0.51
    ៤
    0.50
     Нико
    0.48
    ztal
    0.48
    ędzynarod
    0.47
    actus
    0.46
    vonne
    0.46
    ontiti
    0.46
     લગભગ
    0.45
    POSITIVE LOGITS
     to
    0.56
     insights
    0.55
     jackpot
    0.55
     other
    0.54
     reactions
    0.54
     a
    0.54
     sour
    0.53
     closed
    0.52
     isolation
    0.52
     rows
    0.52
    Activations Density 0.000%

    No Known Activations