© 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. 109068
    Prev
    Next
    INDEX
    Explanations

    code, data, and general concepts

    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
    ଳ
    0.57
     podpor
    0.47
     variés
    0.47
     conteudo
    0.46
    ścić
    0.46
     contenuti
    0.44
     pouvaient
    0.44
     contenus
    0.44
     conteúdos
    0.43
    ل
    0.43
    POSITIVE LOGITS
    dokument
    0.47
     และ
    0.45
    酝
    0.44
     सदस्य
    0.42
     เนื่องจาก
    0.42
     मानस
    0.42
     Humane
    0.41
    parent
    0.41
     जून
    0.41
     वह
    0.41
    Activations Density 0.008%

    No Known Activations