© 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. 8535
    Prev
    Next
    INDEX
    Explanations

    separating list items

    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
    n
    0.95
    ference
    0.89
    да
    0.85
    ке
    0.84
    cimiento
    0.84
    ar
    0.83
    araja
    0.81
    િ
    0.81
     announcements
    0.79
    на
    0.79
    POSITIVE LOGITS
    𝗔
    0.90
    ר
    0.88
     mingled
    0.88
    Ρ
    0.88
    사와
    0.87
     जरिए
    0.86
    ו
    0.85
    EX
    0.81
    𝐌
    0.81
     Qualquer
    0.81
    Activations Density 0.564%

    No Known Activations