© 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. 197510
    Prev
    Next
    INDEX
    Explanations

    know this your connection

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

    jual belimercenarybattleweaponcoordinates

    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
     现在
    0.46
     Jane
    0.46
    Rejected
    0.43
    揶
    0.43
     बेसब्री
    0.42
    䒑
    0.42
     اك
    0.42
    }-${
    0.42
    ปัจจุบัน
    0.42
     Claude
    0.42
    POSITIVE LOGITS
    istem
    0.50
    нера
    0.50
    hacking
    0.50
    emerg
    0.49
    venidas
    0.49
    IR
    0.48
    çay
    0.48
    alin
    0.47
    norms
    0.47
     isop
    0.46
    Activations Density 0.000%

    No Known Activations