© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168423
    Prev
    Next
    INDEX
    Explanations

    specific explanations for context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    bron
    0.50
     ait
    0.47
    跟大家
    0.43
     sommer
    0.43
    dor
    0.42
    mon
    0.41
    were
    0.41
    ś
    0.41
    arı
    0.40
     linn
    0.40
    POSITIVE LOGITS
    ي
    0.55
    替え
    0.49
     допуска
    0.49
    كثر
    0.48
    力
    0.48
     اكثر
    0.47
    sız
    0.47
     කරයි
    0.45
     أكثر
    0.45
    加えて
    0.44
    Activations Density 0.000%

    No Known Activations