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-65K
    4. 2744
    Prev
    Next
    INDEX
    Explanations

    erupting sounds

    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
    ်
    0.66
    ்ப
    0.66
     dynamically
    0.66
    iosam
    0.65
    manam
    0.64
    Ų
    0.59
    ێت
    0.58
    ाब
    0.57
    menos
    0.55
    TABLE
    0.55
    POSITIVE LOGITS
    ashing
    0.99
    udge
    0.95
    acking
    0.86
    umbling
    0.86
    abbing
    0.82
    umps
    0.79
    ack
    0.79
    uddle
    0.79
    unk
    0.79
    unky
    0.78
    Activations Density 0.118%

    No Known Activations