© 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. 14342
    Prev
    Next
    INDEX
    Explanations

    CAN bus

    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
     acidity
    1.02
     ancest
    0.91
    ב
    0.90
     acondicionado
    0.87
     externe
    0.86
     uninhab
    0.86
     élevée
    0.86
     undisputed
    0.83
     immort
    0.82
     licenciado
    0.82
    POSITIVE LOGITS
    1
    1.41
    8
    1.22
    7
    1.20
    2
    1.17
    5
    1.16
    ene
    1.06
    erm
    1.05
    ek
    1.02
    um
    1.00
    rat
    0.98
    Activations Density 0.048%

    No Known Activations