© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 598
    Prev
    Next
    INDEX
    Explanations

    vector, target, temporal, retro, authorization

    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_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
     o
    1.76
     *
    1.70
     que
    1.66
     a
    1.64
    ↵↵
    1.59
     
    1.58
     on
    1.50
     at
    1.49
     to
    1.48
     in
    1.48
    POSITIVE LOGITS
     ſ
    1.70
     인한
    1.66
     mln
    1.62
    तालों
    1.55
     Announces
    1.55
     Theological
    1.54
    MNumber
    1.54
    𝑆
    1.54
     말미암아
    1.53
     Womens
    1.52
    Activations Density 3.073%

    No Known Activations