© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149035
    Prev
    Next
    INDEX
    Explanations

    documentation links on readthedocs.io

    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
    #####
    0.79
    Jac
    0.72
    აგ
    0.67
    Keychain
    0.66
     আজাদ
    0.66
     pink
    0.65
    iable
    0.65
    ######
    0.65
    Los
    0.64
     প্যাকে
    0.64
    POSITIVE LOGITS
     WorldCat
    0.74
     Übersetzung
    0.74
     stara
    0.73
     홈페이지
    0.71
     изпол
    0.71
     år
    0.70
    cluso
    0.70
     ರಚ
    0.69
     posibilidad
    0.69
    vané
    0.69
    Activations Density 0.001%

    No Known Activations