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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 149203
    Prev
    Next
    INDEX
    Explanations

    introductions, understanding, academic numbering

    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_29_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
     ६
    0.87
     ৬
    0.76
     ५
    0.73
     শতকরা
    0.72
     सटी
    0.72
     algéb
    0.71
     ४
    0.71
    五
    0.71
    пру
    0.68
    বক
    0.68
    POSITIVE LOGITS
    intro
    0.88
    Intro
    0.67
     lan
    0.67
    empor
    0.67
    understanding
    0.66
     anyway
    0.66
    Env
    0.65
    understand
    0.64
     intro
    0.63
    attach
    0.62
    Activations Density 0.000%

    No Known Activations