© 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. 131
    Prev
    Next
    INDEX
    Explanations

    words formed from specific prefixes/tokens

    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
     ب
    0.53
     Dynamic
    0.51
     Shared
    0.51
     بم
    0.50
     Forever
    0.46
     بشكل
    0.45
     Head
    0.45
     My
    0.44
     Dynamics
    0.44
     Department
    0.44
    POSITIVE LOGITS
    oufl
    0.50
    iting
    0.49
    ise
    0.49
    ĩ
    0.48
    sit
    0.46
    ilized
    0.45
    uz
    0.45
    r
    0.45
    itting
    0.44
     roug
    0.44
    Activations Density 6.275%

    No Known Activations