© 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-65K
    7. 49960
    Prev
    Next
    INDEX
    Explanations

    leaning against or in

    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_65k_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
    ല്
    0.48
    วิว
    0.47
    询问
    0.47
    镞
    0.46
    点头
    0.46
    耳机
    0.46
     Dokl
    0.45
    ܚ
    0.45
    ionych
    0.45
    訢
    0.45
    POSITIVE LOGITS
     of
    0.53
     biodiversity
    0.51
     that
    0.49
     shifting
    0.49
     mindfulness
    0.49
     mals
    0.48
     to
    0.47
     prevention
    0.46
     socially
    0.46
     awareness
    0.46
    Activations Density 0.008%

    No Known Activations