© 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. 44815
    Prev
    Next
    INDEX
    Explanations

    calves raises

    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
    ה
    1.45
    dı
    1.38
    ี
    1.38
    עים
    1.37
    ా
    1.36
    ਾ
    1.36
     montage
    1.34
    er
    1.33
    ری
    1.32
     Alcan
    1.29
    POSITIVE LOGITS
    ip
    1.73
    uk
    1.45
    ’
    1.45
    い
    1.38
    ।’
    1.36
    țele
    1.32
    ।
    1.30
    I
    1.29
    ota
    1.28
    ।”
    1.25
    Activations Density 0.011%

    No Known Activations