© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112313
    Prev
    Next
    INDEX
    Explanations

    language and education 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
     wersji
    0.50
    ę
    0.46
    Х
    0.45
    ॲ
    0.44
    ug
    0.43
    杽
    0.43
    ৭
    0.43
    ၆
    0.42
     serii
    0.41
    ip
    0.41
    POSITIVE LOGITS
    coded
    0.54
     schooling
    0.47
    baked
    0.46
    quelle
    0.46
    Collective
    0.46
    ignore
    0.44
     (\<
    0.43
     ignore
    0.42
    Hö
    0.42
    biased
    0.42
    Activations Density 0.003%

    No Known Activations