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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 999
    Prev
    Next
    INDEX
    Explanations

    National followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ש
    2.03
    t
    1.88
    ிஸ்த
    1.87
    ний
    1.81
     padrão
    1.81
    멧
    1.80
    zyć
    1.77
     estándar
    1.75
     veik
    1.70
    dır
    1.70
    POSITIVE LOGITS
    са
    1.88
    ל
    1.84
    qu
    1.77
    ities
    1.68
     subjecting
    1.66
    ס
    1.64
    ively
    1.55
     człon
    1.53
    ့
    1.52
    ization
    1.50
    Activations Density 0.011%

    No Known Activations