© 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. 169920
    Prev
    Next
    INDEX
    Explanations

    describing features or specifications

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

    need a, his legacy, impact quality, an abstraction

    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
     realmente
    0.44
    σεων
    0.44
     আসলে
    0.41
    
    0.40
     sheared
    0.40
    snow
    0.39
     الاخير
    0.39
    פ
    0.39
     היום
    0.39
    잖아요
    0.38
    POSITIVE LOGITS
     Ríos
    0.52
    嚧
    0.50
     mnog
    0.49
    ോഗ്യ
    0.48
     možno
    0.48
    梼
    0.48
     eko
    0.47
    હેર
    0.46
     écologique
    0.46
     系统
    0.45
    Activations Density 0.000%

    No Known Activations