© 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. 6845
    Prev
    Next
    INDEX
    Explanations

    spa day or treatments

    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
    ي
    1.12
    י
    1.06
    й
    1.02
    ך
    1.00
    ча
    0.97
    ﯽ
    0.84
    ̷
    0.83
    ки
    0.83
     separatist
    0.82
    פ
    0.81
    POSITIVE LOGITS
    其他
    1.20
    ının
    1.20
    Según
    1.16
     perdió
    1.13
    ش
    1.13
    ile
    1.09
    的工作
    1.09
     прежде
    1.08
     caída
    1.06
    번째
    1.06
    Activations Density 0.001%

    No Known Activations