© 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. 33310
    Prev
    Next
    INDEX
    Explanations

    assets, email, enamel, media, impairments, uterus

    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
    ↵
    0.45
    .
    0.42
    ey
    0.42
     fireplace
    0.40
    shader
    0.38
     puse
    0.38
     bacon
    0.37
    end
    0.37
    top
    0.37
     processing
    0.37
    POSITIVE LOGITS
     बाकी
    0.48
     преду
    0.45
    踌
    0.45
    疡
    0.45
     इतर
    0.44
     информационной
    0.44
    वैसे
    0.44
    장은
    0.43
     స్వాధీ
    0.43
     विविध
    0.43
    Activations Density 0.010%

    No Known Activations