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. 6478
    Prev
    Next
    INDEX
    Explanations

    define

    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
    いた
    1.91
    रा
    1.69
    ING
    1.69
    ள்ளது
    1.66
    AH
    1.66
    ABIL
    1.63
    म
    1.63
    AYA
    1.61
    IE
    1.59
    ORA
    1.58
    POSITIVE LOGITS
    sciences
    1.88
     dasar
    1.76
     prostaglandins
    1.59
    xious
    1.57
     kimia
    1.55
    ни
    1.51
     rõ
    1.51
     thấp
    1.48
    ୟ
    1.48
    sko
    1.47
    Activations Density 0.130%

    No Known Activations