© 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. 44796
    Prev
    Next
    INDEX
    Explanations

    openpyxl library

    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
    es
    0.98
    zione
    0.90
    ud
    0.88
     prosent
    0.88
    men
    0.87
     či
    0.87
    s
    0.85
    reme
    0.84
     działa
    0.84
    uie
    0.84
    POSITIVE LOGITS
    я
    0.79
    ం
    0.75
     Collabor
    0.74
    boxylic
    0.73
    мия
    0.73
     chaper
    0.73
    getAsJsonObject
    0.72
    ни
    0.72
    おそらく
    0.71
     undesired
    0.71
    Activations Density 0.000%

    No Known Activations