© 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. 13608
    Prev
    Next
    INDEX
    Explanations

    specifications and certifications

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

    specific topics

    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
    (.*
    0.30
    
    0.27
    anesu
    0.25
     информации
    0.25
    
    0.24
    इड
    0.24
    ;//
    0.24
    =",
    0.23
    ssf
    0.23
    atres
    0.23
    POSITIVE LOGITS
     be
    0.36
     że
    0.33
     и
    0.31
     quando
    0.31
     в
    0.31
     are
    0.30
     è
    0.30
     jiné
    0.30
     daripada
    0.30
     أ
    0.29
    Activations Density 0.505%

    No Known Activations