© 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. 16-GEMMASCOPE-2-RES-262K
    4. 41649
    Prev
    Next
    INDEX
    Explanations

    patting or petting

    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_16_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
     survives
    0.68
    ב
    0.61
     escaped
    0.59
     suffers
    0.59
     incapacitated
    0.59
     incapac
    0.58
     escape
    0.58
     retains
    0.57
     floated
    0.56
     reproach
    0.56
    POSITIVE LOGITS
    重要
    0.55
    在
    0.55
     более
    0.54
    组成
    0.54
    更为
    0.54
    发展
    0.53
    充分
    0.53
    पणे
    0.53
    在高
    0.53
     университета
    0.53
    Activations Density 0.000%

    No Known Activations