© 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. 6517
    Prev
    Next
    INDEX
    Explanations

    URLs with specific continuations like `site`, `op`, `cli`, `weather`, `quick`, `how`, `blog`

    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
     paralysie
    0.21
     backstory
    0.20
     oryg
    0.19
     beper
    0.19
    味料
    0.19
     marginTop
    0.18
    闓
    0.18
     cityName
    0.18
     biskup
    0.18
     njemu
    0.18
    POSITIVE LOGITS
    ;
    0.24
    security
    0.23
    data
    0.23
    utils
    0.22
    config
    0.22
    api
    0.22
    da
    0.22
    scripts
    0.22
    ui
    0.21
    register
    0.21
    Activations Density 0.264%

    No Known Activations