© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1086
    Prev
    Next
    INDEX
    Explanations

    technical concepts and dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     Tactics
    1.10
    Š
    1.09
     Spitzen
    1.02
    Ž
    1.02
     cynicism
    1.01
     Turbine
    1.01
     Symphony
    0.99
     Š
    0.99
    Crisis
    0.99
     Slash
    0.98
    POSITIVE LOGITS
     във
    0.73
    imiento
    0.71
     уста
    0.69
     in
    0.69
     doo
    0.68
     ста
    0.67
     co
    0.67
    imento
    0.67
    ậy
    0.65
    फॉर्मेशन
    0.63
    Activations Density 2.920%

    No Known Activations