© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11258
    Prev
    Next
    INDEX
    Explanations

    digits and short strings

    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
    for
    1.12
    _)
    1.02
    ونم
    0.99
    缭
    0.92
    and
    0.88
    iyaç
    0.88
    ه
    0.88
    槅
    0.88
    ”)
    0.87
    ),”
    0.87
    POSITIVE LOGITS
    4
    1.73
    7
    1.59
    5
    1.57
    9
    1.53
    8
    1.52
    2
    1.51
    6
    1.49
    3
    1.46
    1
    1.40
     a
    1.30
    Activations Density 0.037%

    No Known Activations