© 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-65K
    7. 193
    Prev
    Next
    INDEX
    Explanations

    states of being

    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_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
    ع
    0.97
    ו
    0.94
    ל
    0.92
    ת
    0.84
    в
    0.84
    ти
    0.82
    علم
    0.82
    ش
    0.82
    د
    0.78
    ק
    0.77
    POSITIVE LOGITS
     are
    0.95
    0.80
    ının
    0.63
     è
    0.61
     LHC
    0.61
     pathogenic
    0.60
     ARE
    0.59
     at
    0.57
     mutta
    0.57
     CCI
    0.56
    Activations Density 1.128%

    No Known Activations