© 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. 54263
    Prev
    Next
    INDEX
    Explanations

    reason for explanation

    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
    alne
    0.59
    嘊
    0.55
    <unused1041>
    0.52
     ۋە
    0.52
    Imidazole
    0.52
     በር
    0.51
    㧕
    0.51
    ப
    0.51
    蕌
    0.50
    სახ
    0.49
    POSITIVE LOGITS
    Ⓡ
    0.47
     trying
    0.45
     gases
    0.45
     chaos
    0.44
     reunion
    0.44
     compensation
    0.44
     salvo
    0.42
     heritage
    0.41
    0.41
     rack
    0.40
    Activations Density 0.009%

    No Known Activations