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. 4302
    Prev
    Next
    INDEX
    Explanations

    punchy, messiness, ugliness

    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
     युग्
    0.65
     למ
    0.65
    <unused442>
    0.64
    Gra
    0.64
     धूम
    0.63
    Burning
    0.63
     Desk
    0.63
    Array
    0.63
     מ
    0.62
     بى
    0.61
    POSITIVE LOGITS
    iness
    2.98
    iest
    2.50
    ier
    2.29
    ily
    2.23
    y
    2.23
    yness
    2.16
    INESS
    2.13
    IER
    1.71
    yp
    1.68
    y
    1.61
    Activations Density 0.351%

    No Known Activations