© 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. 116990
    Prev
    Next
    INDEX
    Explanations

    If then

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

    safety, mutation, CRT, warning

    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
     должен
    0.45
     actualmente
    0.44
     ника
    0.43
    ລິ
    0.43
     componentes
    0.42
     mengucapkan
    0.42
    OSO
    0.42
    );\
    0.42
     únicamente
    0.42
     அமைக்க
    0.41
    POSITIVE LOGITS
     tendency
    0.50
     Haley
    0.48
     practice
    0.48
    തര
    0.45
     probability
    0.45
    ya
    0.44
     Practice
    0.44
     Rang
    0.44
     Jiangsu
    0.44
    ća
    0.44
    Activations Density 0.000%

    No Known Activations