© 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. 18731
    Prev
    Next
    INDEX
    Explanations

    display or hide UI elements

    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
    ABASE
    0.42
    מח
    0.40
    モーション
    0.39
    🔄
    0.37
    FORMANCE
    0.37
    CHUNK
    0.37
    chsler
    0.36
    爌
    0.36
     vertebrates
    0.35
    Ŋ
    0.35
    POSITIVE LOGITS
     hidden
    0.96
    hidden
    0.92
     Hidden
    0.86
     hide
    0.85
    Hidden
    0.85
     hiding
    0.84
    setVisible
    0.83
    隐藏
    0.83
     Hide
    0.82
    hide
    0.81
    Activations Density 0.074%

    No Known Activations