© 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. 244851
    Prev
    Next
    INDEX
    Explanations

    before or after punctuation

    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
     своє
    0.53
     EHR
    0.48
     主要
    0.46
    貘
    0.45
     እና
    0.44
    كا
    0.44
     這
    0.44
     চাকরির
    0.44
     التعليم
    0.44
    beelding
    0.43
    POSITIVE LOGITS
    िप्स
    0.46
    ඤ
    0.45
    from
    0.45
    ifornia
    0.43
    sadpoetry
    0.42
    ikin
    0.42
    tod
    0.42
    rs
    0.41
     excepted
    0.41
    itatively
    0.41
    Activations Density 0.001%

    No Known Activations