© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 99875
    Prev
    Next
    INDEX
    Explanations

    state/implies/guiding/doing/chest

    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_40_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
    ทรั
    0.38
    Vault
    0.38
    appar
    0.38
    acotta
    0.37
    蝣
    0.36
    孔
    0.34
     autom
    0.34
    န္
    0.33
    会将
    0.33
    竖
    0.32
    POSITIVE LOGITS
     tries
    0.42
     limes
    0.41
     loan
    0.41
    🇱
    0.40
     thesis
    0.39
     исходя
    0.39
     averages
    0.39
     PRICES
    0.39
    pues
    0.39
     sweet
    0.39
    Activations Density 0.000%

    No Known Activations