© 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. 44940
    Prev
    Next
    INDEX
    Explanations

    many generations

    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
     locu
    0.90
     ultime
    0.83
    ᱞ
    0.80
     civile
    0.79
     здійсню
    0.79
     utilizan
    0.78
     nici
    0.77
     tentativo
    0.77
     sản
    0.76
     gratuite
    0.76
    POSITIVE LOGITS
    ী
    0.89
    ud
    0.88
    ING
    0.84
    ру
    0.84
    z
    0.83
    ων
    0.83
    ุ
    0.77
    π
    0.77
    INY
    0.76
    й
    0.75
    Activations Density 0.000%

    No Known Activations