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. 1059
    Prev
    Next
    INDEX
    Explanations

    art nouveau, art deco

    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
    er
    1.07
    ה
    0.79
    요
    0.76
     अंतर्गत
    0.74
    oğlu
    0.73
    र
    0.73
    Parsing
    0.72
    果
    0.71
     види
    0.71
    ⤦
    0.70
    POSITIVE LOGITS
    ifical
    1.69
    ifice
    1.59
    istically
    1.56
    istic
    1.51
    ísticas
    1.47
     nouveau
    1.43
    esian
    1.41
    istry
    1.36
    ful
    1.35
     deco
    1.30
    Activations Density 0.032%

    No Known Activations