© 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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 19406
    Prev
    Next
    INDEX
    Explanations

    plan, project, proposal, research, case study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    #
    1.58
    altura
    1.30
    #{
    1.28
    #,
    1.20
    अगर
    1.17
    #.
    1.17
    yard
    1.16
    $("
    1.15
    huis
    1.11
    however
    1.11
    POSITIVE LOGITS
     APPENDIX
    1.42
     Deloitte
    1.41
     Obtaining
    1.26
     noqa
    1.25
     Curiosity
    1.22
     Werner
    1.22
    𝗔
    1.19
    芠
    1.18
     Fancy
    1.18
     Frontend
    1.17
    Activations Density 0.005%

    No Known Activations