© 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. 243500
    Prev
    Next
    INDEX
    Explanations

    console commands

    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
    р
    0.59
    会長
    0.52
     micrograms
    0.49
     deix
    0.49
    クリニック
    0.49
    鋤
    0.49
     diverting
    0.48
     cui
    0.48
     whose
    0.48
    わ
    0.46
    POSITIVE LOGITS
    urm
    0.51
    urring
    0.48
    loggedIn
    0.46
    idays
    0.45
    OrderID
    0.44
     আবহ
    0.44
    atcher
    0.44
    类似于
    0.43
    intaan
    0.43
    发生
    0.42
    Activations Density 0.000%

    No Known Activations