© 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. 10895
    Prev
    Next
    INDEX
    Explanations

    performing tasks or duties

    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
    d
    2.36
    t
    2.17
    ਰ
    2.14
    m
    2.09
    də
    1.84
    ’
    1.80
    АК
    1.79
    ts
    1.75
    드는
    1.72
    <0xB2>
    1.69
    POSITIVE LOGITS
    ки
    2.11
     admirably
    2.11
    ف
    2.11
    ે
    2.02
    aient
    1.87
    ли
    1.85
     éventuellement
    1.83
    ो
    1.83
    ى
    1.83
    いない
    1.79
    Activations Density 0.045%

    No Known Activations