© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53033
    Prev
    Next
    INDEX
    Explanations

    keep children away

    np_acts-logits-general · gemini-2.5-flash-lite

    keep children away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ভিল
    0.50
    filters
    0.49
    騁
    0.48
    avenir
    0.47
    業界
    0.47
    FormParams
    0.47
    chyné
    0.46
     promotes
    0.46
    apiKey
    0.46
    idn
    0.46
    POSITIVE LOGITS
     声
    0.40
     પોતા
    0.39
    ’
    0.39
     occip
    0.38
    రు
    0.38
     sone
    0.37
     استعمال
    0.37
     وسلم
    0.37
    '
    0.36
     Ophthalm
    0.36
    Activations Density 0.001%

    No Known Activations