© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4094
    Prev
    Next
    INDEX
    Explanations

    return

    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
    s
    2.03
    ्स
    1.88
    ς
    1.79
    𝐬
    1.66
    𝐭
    1.57
    𝘀
    1.56
     către
    1.52
    ს
    1.46
     enk
    1.42
    త
    1.42
    POSITIVE LOGITS
    ar
    2.56
    an
    2.39
    ان
    2.11
    на
    2.09
    zelfde
    2.06
    is
    1.95
    el
    1.95
    larda
    1.90
    quela
    1.84
    on
    1.77
    Activations Density 1.443%

    No Known Activations