© 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. 64663
    Prev
    Next
    INDEX
    Explanations

    hate technology, blame

    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
    c
    0.44
     dispute
    0.43
    itti
    0.43
    veland
    0.43
     instant
    0.43
     family
    0.42
     â
    0.42
     그다
    0.42
     relocation
    0.42
    ilh
    0.41
    POSITIVE LOGITS
    Для
    0.50
    isering
    0.47
    Об
    0.46
    тров
    0.44
    索
    0.43
    ↵↵
    0.43
    ceptors
    0.42
    قت
    0.42
     Kõ
    0.42
    ности
    0.41
    Activations Density 0.002%

    No Known Activations