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-262K
    4. 612
    Prev
    Next
    INDEX
    Explanations

    like gradient descent

    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
    âts
    0.56
    ⁢
    0.56
    ‭
    0.56
    ângulo
    0.56
     Tatha
    0.55
    ⁣
    0.55
    ⁤
    0.54
    ᠣ
    0.54
    hung
    0.54
    ilización
    0.54
    POSITIVE LOGITS
     E
    0.56
     Why
    0.55
     Men
    0.52
     Analyze
    0.51
     Education
    0.51
     Explain
    0.50
     User
    0.50
     Team
    0.50
     Good
    0.50
     Where
    0.50
    Activations Density 0.000%

    No Known Activations