© 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. 8599
    Prev
    Next
    INDEX
    Explanations

    photography, philosophy, -ism

    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
    はある
    1.71
    ם
    1.59
    ן
    1.55
    ungs
    1.50
    করণ
    1.48
    습니다
    1.47
    事で
    1.34
    ০০০
    1.34
    ق
    1.34
    了一眼
    1.32
    POSITIVE LOGITS
    ли
    2.50
    ை
    1.88
    ์
    1.85
    ي
    1.70
    ం
    1.66
    客様
    1.62
    द
    1.58
    ı
    1.55
    ન
    1.53
    nels
    1.52
    Activations Density 0.261%

    No Known Activations