© 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-65K
    7. 40223
    Prev
    Next
    INDEX
    Explanations

    informed consent / crime / distress

    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_65k_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
    ote
    0.47
     those
    0.46
     the
    0.45
    னில்
    0.43
     '%
    0.42
    тение
    0.41
     Comp
    0.41
     each
    0.41
     Pre
    0.41
    ח
    0.40
    POSITIVE LOGITS
     brushless
    0.47
     alleviation
    0.46
     préféré
    0.45
    巳
    0.45
     اگ
    0.45
    ാരോഗ്യ
    0.45
     ጥሩ
    0.44
    Safety
    0.44
     během
    0.43
     ราศี
    0.43
    Activations Density 0.049%

    No Known Activations