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. 1267
    Prev
    Next
    INDEX
    Explanations

    magical formula

    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
     Floret
    0.63
    ontinuous
    0.59
    噙
    0.59
     quartile
    0.59
     hydroly
    0.58
    <unused24>
    0.57
    煦
    0.57
    🚧
    0.57
     lather
    0.56
    蚝
    0.56
    POSITIVE LOGITS
     magical
    2.63
     magic
    2.52
     mystical
    2.50
     supernatural
    2.45
     paranormal
    2.17
     mysticism
    2.10
     mystic
    2.08
    magic
    2.02
     magia
    2.01
     Magical
    2.01
    Activations Density 0.732%

    No Known Activations