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

    Neuronpedia

    Jacobian LensNEW
    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. 10128
    Prev
    Next
    INDEX
    Explanations

    end of sentence

    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
     uneven
    0.57
     کریں
    0.54
     Keystone
    0.54
     unfl
    0.52
     Ver
    0.51
     ›
    0.50
     unwavering
    0.50
    läge
    0.50
     ongoing
    0.49
     Onder
    0.49
    POSITIVE LOGITS
    та
    0.71
    []');
    0.64
     университе
    0.63
    가
    0.63
    enced
    0.62
    했던
    0.62
    ísim
    0.62
    ('['
    0.62
    ()'
    0.62
    我想
    0.61
    Activations Density 0.000%

    No Known Activations