© 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. 220659
    Prev
    Next
    INDEX
    Explanations

    employment relationship, user experience, customer service

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

    big gestures or small

    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
     автоматтары
    0.48
     оке
    0.46
     ойной
    0.46
    
    0.45
     memoranda
    0.44
     baloncesto
    0.43
    фей
    0.43
    곍
    0.43
     exempl
    0.42
     exemplary
    0.42
    POSITIVE LOGITS
     Celle
    0.46
    intestinal
    0.46
     Halle
    0.45
     Rang
    0.45
    antib
    0.44
     เจอ
    0.44
    variety
    0.44
    stilling
    0.44
     गेल्या
    0.44
    amental
    0.43
    Activations Density 0.001%

    No Known Activations