© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48156
    Prev
    Next
    INDEX
    Explanations

    Dallas locations and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hunan
    0.40
    iob
    0.38
     wu
    0.38
     tend
    0.38
    节
    0.37
     barbed
    0.37
     spacing
    0.36
     sugar
    0.36
    人数
    0.36
     मात्रा
    0.35
    POSITIVE LOGITS
    Dallas
    1.06
     Dallas
    1.00
     Dall
    0.57
    ダル
    0.54
     달
    0.53
    Newcastle
    0.52
     Newcastle
    0.50
     Plano
    0.50
     dall
    0.48
     हैदराबाद
    0.48
    Activations Density 0.012%

    No Known Activations