© 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. 231362
    Prev
    Next
    INDEX
    Explanations

    bringing worlds, picked this

    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
    s
    0.58
     or
    0.54
    オープン
    0.50
    インターネット
    0.50
     In
    0.49
    の
    0.49
    ブ
    0.49
    ס
    0.48
    적
    0.48
     not
    0.48
    POSITIVE LOGITS
     jährlich
    0.52
     परियोजनाओं
    0.51
    uite
    0.50
    arli
    0.49
    தேசம்
    0.49
     каждом
    0.48
    शिक्ष
    0.46
    अच्छ
    0.46
    GTBase
    0.46
    chalk
    0.46
    Activations Density 0.001%

    No Known Activations