Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3513
    Prev
    Next
    INDEX
    Explanations

    into, without, in, thoroughly

    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_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
     gelungen
    0.67
     bleiben
    0.65
    ="'$(
    0.61
     seterusnya
    0.59
     zroz
    0.58
     quedando
    0.58
     continuando
    0.58
    uldade
    0.58
     Несмотря
    0.58
     Meski
    0.58
    POSITIVE LOGITS
     onto
    0.72
     (
    0.61
     into
    0.60
    onto
    0.60
     either
    0.54
    []
    0.53
     separately
    0.52
     yourself
    0.50
      
    0.49
     vào
    0.49
    Activations Density 0.183%

    No Known Activations