© 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. 58911
    Prev
    Next
    INDEX
    Explanations

    following hacks claim access

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

    avoiding fabrication or pretense

    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
     źród
    0.44
     clerks
    0.43
     영화
    0.42
    រ
    0.42
     복
    0.42
     seamen
    0.40
     국내
    0.40
    齒
    0.40
    ODBA
    0.39
     wagg
    0.38
    POSITIVE LOGITS
    əl
    0.48
    １
    0.47
     UIKit
    0.44
     poiché
    0.43
    lü
    0.42
    tolerance
    0.41
    âche
    0.41
    ்துற
    0.40
    陉
    0.40
     nic
    0.39
    Activations Density 0.000%

    No Known Activations