© 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. 231516
    Prev
    Next
    INDEX
    Explanations

    expected you online messages risk

    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
     thoracique
    0.55
    umlahan
    0.54
     ktoré
    0.50
     ไหร่
    0.50
     እድ
    0.50
     শ্
    0.50
    珲
    0.49
    𝐬
    0.48
    百科
    0.48
    格子
    0.48
    POSITIVE LOGITS
     for
    0.59
     have
    0.57
            
    0.57
     #
    0.57
     be
    0.54
     didn
    0.53
     from
    0.53
     really
    0.52
     General
    0.52
    #
    0.51
    Activations Density 0.001%

    No Known Activations