© 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. 27249
    Prev
    Next
    INDEX
    Explanations

    Jehovah's Witnesses

    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
     pasting
    0.59
     having
    0.59
     looking
    0.56
    y
    0.55
    itag
    0.54
     ascend
    0.54
     grew
    0.52
     Pryor
    0.51
     heartbroken
    0.50
     stamping
    0.50
    POSITIVE LOGITS
    ل
    0.68
    他的
    0.63
    城市的
    0.58
    𝗅
    0.56
    ؟.
    0.54
    萜
    0.53
     그는
    0.53
     ඔහුගේ
    0.52
    ล
    0.52
    īs
    0.52
    Activations Density 0.001%

    No Known Activations