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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 52841
    Prev
    Next
    INDEX
    Explanations

    emotional dysregulation and identity fragmentation

    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
     hemorrhagic
    0.75
    ⎞
    0.74
     cucumbers
    0.74
    靴
    0.72
     রব
    0.71
     preschoolers
    0.70
     jeden
    0.69
    ধারা
    0.68
     percussion
    0.68
     tulip
    0.68
    POSITIVE LOGITS
    chee
    0.81
    过
    0.76
    孃
    0.75
    acky
    0.74
     restructured
    0.74
     Ters
    0.73
     schop
    0.72
     起
    0.72
    éristiques
    0.71
    ដើ
    0.70
    Activations Density 0.000%

    No Known Activations