© 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. 209810
    Prev
    Next
    INDEX
    Explanations

    daily method of operation

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

    diode-bridge compressor

    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
    u
    0.63
    y
    0.52
    ado
    0.49
     Demo
    0.49
    solid
    0.47
    o
    0.47
    ierte
    0.47
    cellent
    0.47
    en
    0.46
     Award
    0.46
    POSITIVE LOGITS
     комбина
    0.55
    ྃ
    0.52
     observaciones
    0.50
     компози
    0.48
    မိ
    0.47
    समाचार
    0.47
    ૧
    0.47
    зив
    0.46
     খাওয়
    0.46
     anaemia
    0.46
    Activations Density 0.001%

    No Known Activations