Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 52954
    Prev
    Next
    INDEX
    Explanations

    walnuts

    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
    ać
    0.78
    砧
    0.76
    ameth
    0.75
     ይሰ
    0.75
     निगाह
    0.75
     abstractions
    0.75
    ักษณ์
    0.74
    แทน
    0.74
     sinks
    0.74
    amard
    0.73
    POSITIVE LOGITS
    rus
    0.90
    llä
    0.86
    <unused95>
    0.78
    alese
    0.76
     IList
    0.74
     ویئر
    0.73
    fortunately
    0.72
    Surprisingly
    0.72
    gressive
    0.71
    นต์
    0.70
    Activations Density 0.001%

    No Known Activations