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-65K
    4. 41387
    Prev
    Next
    INDEX
    Explanations

    technical and scientific references

    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_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
    jus
    0.74
    December
    0.69
     मोटा
    0.68
     jus
    0.68
    最高
    0.68
    adece
    0.67
    IsMethod
    0.66
    ∬
    0.65
    Alors
    0.65
    ům
    0.65
    POSITIVE LOGITS
     ብ
    0.77
    hent
    0.70
     sayings
    0.69
     perin
    0.68
     accepting
    0.68
    ínio
    0.67
     ያ
    0.65
    Nancy
    0.64
     mythical
    0.64
     ತೆ
    0.63
    Activations Density 0.000%

    No Known Activations