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. 464
    Prev
    Next
    INDEX
    Explanations

    English

    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
    ्स
    2.03
    larda
    1.89
    قوق
    1.84
    ીર
    1.75
    彭
    1.72
    אנ
    1.70
    Hình
    1.68
    ્સ
    1.66
    אן
    1.65
    습니다
    1.59
    POSITIVE LOGITS
    é
    2.44
    sourceforge
    2.02
    ли
    1.95
    speaking
    1.82
     muffins
    1.82
    llll
    1.81
    wort
    1.80
    нки
    1.80
    л
    1.77
    т
    1.76
    Activations Density 0.041%

    No Known Activations