© 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. 6009
    Prev
    Next
    INDEX
    Explanations

    preserve or illusion

    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
    it
    2.20
    ci
    2.14
    ่
    2.09
    ている
    1.86
    ți
    1.84
     ভিত্তিতে
    1.81
     Oils
    1.81
    ן
    1.81
    por
    1.80
    pa
    1.75
    POSITIVE LOGITS
    ী
    2.98
    ATION
    2.89
    ی
    2.77
    ്യ
    2.61
    ीकरण
    2.58
    ing
    2.53
    ו
    2.44
    ление
    2.42
    raulic
    2.42
    ো
    2.42
    Activations Density 0.144%

    No Known Activations