© 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. 102008
    Prev
    Next
    INDEX
    Explanations

    original or own carton boxes

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

    unique features, call buttons, then burn, lines, black areas, ink, circular, blooming, lemon

    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
    Vere
    0.47
    R
    0.46
    ް
    0.44
    elje
    0.43
    Pere
    0.43
    Cab
    0.42
    ož
    0.41
     umož
    0.41
     verbessern
    0.41
     brez
    0.41
    POSITIVE LOGITS
     fgets
    0.50
    oids
    0.50
    нім
    0.47
     Patents
    0.46
    一看
    0.46
    ки
    0.46
    й
    0.45
     ні
    0.45
    দিক
    0.45
     phthal
    0.45
    Activations Density 0.000%

    No Known Activations