© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 44119
    Prev
    Next
    INDEX
    Explanations

    permeability

    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
    에는
    1.73
    𝑝
    1.71
    
    1.69
    불
    1.65
    scores
    1.64
    pecific
    1.64
    
    1.57
     листопада
    1.55
    ’.”
    1.52
     липня
    1.51
    POSITIVE LOGITS
    ت
    2.56
    t
    2.53
    ار
    2.48
    م
    2.36
    و
    2.30
    تش
    2.28
    ن
    2.23
    تون
    2.22
     Welche
    2.14
    תה
    2.13
    Activations Density 0.009%

    No Known Activations