© 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. 17472
    Prev
    Next
    INDEX
    Explanations

    Sex and the City, Jones, Rom-com

    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
    .
    0.65
    อ
    0.65
    ม
    0.65
    ین
    0.64
    ק
    0.56
    RICT
    0.55
     ই
    0.54
    encia
    0.52
    nd
    0.51
    да
    0.51
    POSITIVE LOGITS
     журнали
    0.57
    ɲ
    0.55
    athan
    0.55
     newsletter
    0.54
     diaries
    0.54
     secretaries
    0.54
     meantime
    0.54
     نویس
    0.53
     söyledi
    0.52
     devo
    0.52
    Activations Density 0.001%

    No Known Activations