© 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. 126954
    Prev
    Next
    INDEX
    Explanations

    to shit, score high, Peru, Approved by, Ask your, Coconut oil

    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
    йти
    0.54
    跹
    0.47
     кра
    0.46
     связан
    0.46
    aminan
    0.46
    ۲۰
    0.44
    imately
    0.44
    кра
    0.44
    ctive
    0.44
     cropping
    0.43
    POSITIVE LOGITS
     Singular
    0.44
    ወስ
    0.44
     diferença
    0.42
    نق
    0.41
    ن
    0.41
     malice
    0.41
    נ
    0.41
    Mor
    0.41
     atributo
    0.40
     wretched
    0.40
    Activations Density 0.004%

    No Known Activations