© 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. 6776
    Prev
    Next
    INDEX
    Explanations

    Here's a concise explanation of the neuron's behavior:`tf` configurations with `contract` or `flags`

    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
    ﺩ
    0.95
    />
    0.89
    هایی
    0.87
     sunken
    0.87
    )]$
    0.86
    =-
    0.86
    ွာ
    0.86
    setTimeout
    0.85
     salário
    0.85
    ঘুম
    0.84
    POSITIVE LOGITS
    ار
    1.34
    ي
    1.11
    ר
    1.10
    ارين
    1.09
     утвержда
    1.09
    ar
    1.01
    不必
    0.98
     ٿ
    0.96
     là
    0.95
     Cre
    0.94
    Activations Density 0.001%

    No Known Activations