Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 511
    Prev
    Next
    INDEX
    Explanations

    branded text

    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
    ighth
    0.56
    hounds
    0.49
    र्देश
    0.47
     geme
    0.47
    RAchievement
    0.47
    ischem
    0.46
    umiem
    0.46
    侔
    0.46
    school
    0.45
    щён
    0.45
    POSITIVE LOGITS
    얕
    0.45
     ITU
    0.43
    쐞
    0.42
     excès
    0.41
    olique
    0.41
    aniu
    0.38
    PELL
    0.38
     combustibles
    0.38
     étaient
    0.38
    ဦ
    0.38
    Activations Density 0.000%

    No Known Activations