© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57903
    Prev
    Next
    INDEX
    Explanations

    section introductions and copyright notices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ույ
    -0.79
     ning
    -0.77
     ἐκ
    -0.76
    Šaltiniai
    -0.76
     τὴν
    -0.73
    聞いた
    -0.73
     presente
    -0.69
    ündig
    -0.69
     หน้า
    -0.68
    Kenmerken
    -0.68
    POSITIVE LOGITS
    <eos>
    4.09
    itous
    0.83
    tować
    0.81
    ulls
    0.79
    ruiter
    0.78
    veloppe
    0.77
    stuffs
    0.77
     protoimpl
    0.76
    ւ
    0.76
    tuch
    0.75
    Activations Density 0.097%

    No Known Activations