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. 998
    Prev
    Next
    INDEX
    Explanations

    divine God consciousness creations

    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
     numerals
    0.48
     numeral
    0.48
    ểm
    0.46
    峹
    0.46
    ंडल
    0.45
     two
    0.45
    й
    0.44
     number
    0.44
     النقطه
    0.44
     ว
    0.42
    POSITIVE LOGITS
     overcoming
    0.45
     tente
    0.45
     considérable
    0.44
     metodologia
    0.44
     gloria
    0.43
     valutazione
    0.41
     alegria
    0.41
     desiderio
    0.41
     energie
    0.41
     apprend
    0.41
    Activations Density 0.175%

    No Known Activations