© 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. 236125
    Prev
    Next
    INDEX
    Explanations

    prevents thinning, anti-theft

    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
    同比增长
    0.52
    냠
    0.49
    와이스
    0.48
    Employee
    0.48
    ஜ
    0.45
    يلات
    0.45
    Bihar
    0.45
    აცია
    0.45
    сла
    0.44
     charismatic
    0.44
    POSITIVE LOGITS
     also
    0.49
    ľad
    0.46
     поч
    0.45
     [§
    0.45
    cett
    0.45
    ること
    0.45
     purport
    0.44
     сход
    0.44
     analyse
    0.44
    krét
    0.44
    Activations Density 0.001%

    No Known Activations