© 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. 86112
    Prev
    Next
    INDEX
    Explanations

    heterosexual couples, rectangular form

    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
    }{
    0.90
    ও
    0.83
    ர்கள்
    0.80
    }_{\
    0.72
    ins
    0.70
    அ
    0.70
    azed
    0.69
    ubs
    0.68
    acion
    0.68
    inas
    0.68
    POSITIVE LOGITS
    лли
    0.82
    rī
    0.73
     Così
    0.71
    ิล
    0.70
    AZIONE
    0.70
     JUnit
    0.70
     I
    0.69
     syscall
    0.68
    Lucene
    0.67
    AN
    0.67
    Activations Density 0.001%

    No Known Activations