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. 29-GEMMASCOPE-2-RES-262K
    4. 821
    Prev
    Next
    INDEX
    Explanations

    its usually followed by context

    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
    EDUC
    0.72
     Nail
    0.71
     ಕಂಡ
    0.69
    WindowState
    0.69
     Validators
    0.68
     billing
    0.67
     Disbursement
    0.67
    蹦
    0.67
     PRODUCTS
    0.66
    બ્
    0.66
    POSITIVE LOGITS
    compound
    0.74
    it
    0.73
    It
    0.71
     it
    0.71
    ga
    0.68
    τσ
    0.67
    rump
    0.64
    మన్
    0.64
    chen
    0.64
    Compound
    0.64
    Activations Density 0.000%

    No Known Activations