© 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-262K
    7. 50941
    Prev
    Next
    INDEX
    Explanations

    moral reasoning, desire, costs

    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
    不上
    0.50
    },{
    0.47
    ン
    0.45
    ває
    0.45
    趣味
    0.44
    時
    0.43
    中
    0.43
    又
    0.43
    蕎
    0.42
    ず
    0.42
    POSITIVE LOGITS
     Defender
    0.53
     Caste
    0.48
     Defenders
    0.47
     Bits
    0.46
    gató
    0.46
     Tackle
    0.46
     Lighting
    0.45
     Accessories
    0.45
     Sharks
    0.45
     व्हेल
    0.45
    Activations Density 0.007%

    No Known Activations