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. 31065
    Prev
    Next
    INDEX
    Explanations

    different business units

    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
    ो
    0.87
     chức
    0.84
    ో
    0.83
     potable
    0.82
     Breaking
    0.80
     depl
    0.80
     độ
    0.79
    US
    0.77
    ﻟ
    0.76
    lığ
    0.75
    POSITIVE LOGITS
     fittings
    0.77
    anthem
    0.71
    parks
    0.67
    شاعرانه
    0.67
    buenas
    0.66
     quartiers
    0.66
    í
    0.65
     fashions
    0.65
    ໍ່
    0.64
     quartos
    0.63
    Activations Density 0.000%

    No Known Activations