© 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. 862
    Prev
    Next
    INDEX
    Explanations

    effects of

    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
    не
    2.09
    ור
    1.48
    हून
    1.45
    ис
    1.45
     fart
    1.44
    ט
    1.40
     lossless
    1.39
     forn
    1.37
     Shout
    1.37
    ফিক
    1.34
    POSITIVE LOGITS
    iv
    1.90
     samping
    1.83
    ik
    1.58
    izienz
    1.48
    ap
    1.47
    ia
    1.47
    ikä
    1.47
    ore
    1.46
     iż
    1.45
    ó
    1.44
    Activations Density 0.064%

    No Known Activations