© 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. 139575
    Prev
    Next
    INDEX
    Explanations

    book and vinyl

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

    create new or develop

    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
     strconv
    0.48
     reconnection
    0.46
    Hungary
    0.42
    整数
    0.41
     intrusion
    0.41
    Enum
    0.40
              
    0.40
     modes
    0.40
    慑
    0.40
     absorption
    0.39
    POSITIVE LOGITS
     ทด
    0.57
     مدرسه
    0.54
     मुद्दों
    0.53
     ขั้น
    0.52
    oprol
    0.51
    dL
    0.51
    කාර
    0.50
     पुस्तकों
    0.50
     Pflege
    0.50
    donor
    0.50
    Activations Density 0.001%

    No Known Activations