© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 112398
    Prev
    Next
    INDEX
    Explanations

    word followed by word

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

    happens when you boil

    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
     läk
    0.53
    脳
    0.49
     surgical
    0.48
     घेतले
    0.48
     psychotic
    0.46
    薬
    0.46
    獅
    0.46
    ებ
    0.45
     রোগে
    0.45
     genomic
    0.45
    POSITIVE LOGITS
    تان
    0.49
    psum
    0.48
     Happens
    0.46
    нами
    0.45
    λαν
    0.45
    softmax
    0.45
    úncia
    0.44
     Happened
    0.43
    lasan
    0.43
     ActiveRecord
    0.43
    Activations Density 0.001%

    No Known Activations