© 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. 11830
    Prev
    Next
    INDEX
    Explanations

    you have a really

    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
     delves
    1.31
     |”
    1.28
    thorace
    1.27
    蹌
    1.23
     glancing
    1.18
    <unused1563>
    1.18
     من
    1.16
     إلى
    1.13
    baseHP
    1.12
     dhinak
    1.11
    POSITIVE LOGITS
    ia
    0.98
    ing
    0.86
    id
    0.83
    u
    0.80
    ren
    0.79
    it
    0.75
    one
    0.74
    ame
    0.74
    er
    0.74
    ie
    0.74
    Activations Density 0.001%

    No Known Activations