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. 9-GEMMASCOPE-2-RES-262K
    4. 7581
    Prev
    Next
    INDEX
    Explanations

    my little

    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_9_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
    '"
    1.33
    '$
    1.21
     ResponseEntity
    1.14
    ="<%=
    1.14
     computerScore
    1.13
     spalle
    1.13
     moż
    1.13
    '.$
    1.10
     chất
    1.08
    ím
    1.06
    POSITIVE LOGITS
    न
    1.32
    फल
    1.31
    O
    1.23
    HOW
    1.18
    ه
    1.15
     beginners
    1.14
    𝙪
    1.12
    Universal
    1.11
    ेन
    1.11
     admirable
    1.10
    Activations Density 0.000%

    No Known Activations