© 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. 43662
    Prev
    Next
    INDEX
    Explanations

    in

    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
     وفي
    1.89
     وبين
    1.71
     cikin
    1.63
    ılarak
    1.62
    外的
    1.43
    𝔱
    1.43
     рынка
    1.42
     kojem
    1.42
    ího
    1.42
     accordance
    1.35
    POSITIVE LOGITS
    >
    1.84
    d
    1.66
    j
    1.65
    س
    1.63
    ம்
    1.59
    ס
    1.49
    1
    1.47
    is
    1.42
    en
    1.41
     এতে
    1.40
    Activations Density 0.014%

    No Known Activations