© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19348
    Prev
    Next
    INDEX
    Explanations

    Pérez explained

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

    exploit, created, played, log

    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
     u
    0.55
     gpu
    0.46
     cpu
    0.44
     oryg
    0.44
     gmin
    0.43
    LIB
    0.43
     kac
    0.42
     cmds
    0.41
    杯
    0.41
    //#
    0.41
    POSITIVE LOGITS
     તમામ
    0.50
     implementação
    0.48
     aplicações
    0.47
     desenvolver
    0.47
     alcanzar
    0.46
     اجيب
    0.46
     அனைவரும்
    0.46
    啫
    0.46
     திரைப்பட
    0.45
     estarán
    0.44
    Activations Density 0.000%

    No Known Activations