© 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. 132398
    Prev
    Next
    INDEX
    Explanations

    decryption licenses

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

    explaining numbers and attempts

    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
     {
    0.51
     Constituency
    0.50
     kWh
    0.48
     *
    0.48
     kiln
    0.48
     Alpha
    0.47
     exactly
    0.46
    ('|
    0.46
     electrical
    0.46
     slush
    0.46
    POSITIVE LOGITS
     ощущение
    0.58
     ощущения
    0.51
    亞洲
    0.51
     семина
    0.50
    rások
    0.49
    すすめ
    0.49
     принцип
    0.49
    சீ
    0.47
    新作
    0.47
     razvoja
    0.47
    Activations Density 0.000%

    No Known Activations