© 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. 231734
    Prev
    Next
    INDEX
    Explanations

    @ verizon.net

    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
    I
    0.47
     I
    0.45
    Ⅰ
    0.44
    다음
    0.44
     regex
    0.44
     Todo
    0.43
    Brown
    0.42
    िफिशियल
    0.42
    ＋
    0.42
    from
    0.42
    POSITIVE LOGITS
     է
    0.52
     eing
    0.52
    nEnter
    0.49
    pieceSelection
    0.47
     einge
    0.45
     Eintritt
    0.45
     ἢ
    0.44
     Hafen
    0.44
     entschied
    0.44
     einer
    0.43
    Activations Density 0.000%

    No Known Activations