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. 17-GEMMASCOPE-2-RES-65K
    4. 47274
    Prev
    Next
    INDEX
    Explanations

    each unit or component

    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_17_width_65k_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
    um
    1.41
    am
    1.39
    igators
    1.37
    igator
    1.33
    n
    1.25
    ur
    1.20
     bothers
    1.15
     enjoined
    1.15
    ون
    1.14
    لل
    1.14
    POSITIVE LOGITS
     হলে
    1.18
     ago
    1.18
    ة
    1.15
    되면
    1.14
     constituye
    1.12
    セル
    1.11
     मापने
    1.11
    日內
    1.10
    ed
    1.09
    পুরে
    1.08
    Activations Density 0.025%

    No Known Activations