© 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. 251239
    Prev
    Next
    INDEX
    Explanations

    East Bengal, Networks and tasks

    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
    िद
    0.48
     нож
    0.46
    йт
    0.45
    罌
    0.45
     infring
    0.45
    UAGE
    0.45
    斧
    0.45
    下跌
    0.44
    っこ
    0.44
    пат
    0.43
    POSITIVE LOGITS
     Merlin
    0.53
     a
    0.52
     Shab
    0.52
     their
    0.51
     '
    0.51
     mer
    0.49
    ◻
    0.48
     reu
    0.48
     Baron
    0.47
     Harrison
    0.47
    Activations Density 0.001%

    No Known Activations