© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103904
    Prev
    Next
    INDEX
    Explanations

    podiatrist, podophilia

    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
    ని
    0.65
    ná
    0.62
    ﺭ
    0.55
     variability
    0.53
    Protocol
    0.53
     protocol
    0.52
    سي
    0.51
    ณ์
    0.51
    äns
    0.51
    lieben
    0.51
    POSITIVE LOGITS
     to
    0.65
    w
    0.63
     ήταν
    0.62
     articoli
    0.61
     возраст
    0.57
     at
    0.56
    uat
    0.56
    hrad
    0.55
     Sought
    0.55
     outubro
    0.54
    Activations Density 0.002%

    No Known Activations