Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3957
    Prev
    Next
    INDEX
    Explanations

    file operations and contexts

    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
    jenigen
    2.11
    나
    1.92
     dobra
    1.86
    ς
    1.80
    ます
    1.76
    سي
    1.73
     mezcla
    1.70
    ü
    1.68
    BE
    1.65
     decimos
    1.63
    POSITIVE LOGITS
    いた
    2.20
    써
    2.03
    ination
    2.02
     punishable
    1.98
    ography
    1.89
    특별시
    1.84
    ান
    1.78
    ך
    1.78
    ্লাহ
    1.74
    😂😂
    1.71
    Activations Density 0.106%

    No Known Activations