© 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. 48125
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    guidance and independence

    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
     Ор
    0.45
    (">
    0.43
    Converted
    0.42
     Lucky
    0.42
     legality
    0.41
    Thrown
    0.41
    螈
    0.41
     '"
    0.40
     Ta
    0.39
    Scient
    0.39
    POSITIVE LOGITS
    pflege
    0.41
    MAD
    0.41
    片
    0.40
     arrivée
    0.40
     esperado
    0.40
     utilizamos
    0.39
    mocks
    0.39
    假的
    0.38
    ファイルの
    0.38
    ,…
    0.37
    Activations Density 0.000%

    No Known Activations