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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 693
    Prev
    Next
    INDEX
    Explanations

    Greek, Spanish, Thai

    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
     BUT
    0.81
    栍
    0.78
     YAML
    0.76
    䖝
    0.72
    龍
    0.72
    ശം
    0.72
    Л
    0.71
    Proyecto
    0.71
    晫
    0.71
     Фор
    0.71
    POSITIVE LOGITS
     οι
    0.88
     những
    0.78
     μια
    0.75
     την
    0.67
     η
    0.63
     la
    0.63
    νοντας
    0.61
     τις
    0.60
     κάτι
    0.59
     تاہم
    0.59
    Activations Density 0.001%

    No Known Activations