© 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. 4241
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    و
    1.88
    ੇ
    1.56
     È
    1.47
    みた
    1.47
    на
    1.43
    ्य
    1.43
    ल
    1.42
     siquiera
    1.38
    おり
    1.36
    i
    1.35
    POSITIVE LOGITS
    ların
    1.70
    ﻂ
    1.47
    лик
    1.45
    ৪
    1.44
    दा
    1.40
    만한
    1.40
    ১০
    1.38
    스를
    1.38
    ۹
    1.36
    GRESS
    1.33
    Activations Density 0.000%

    No Known Activations