© 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-262K
    7. 168850
    Prev
    Next
    INDEX
    Explanations

    android client api

    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_262k_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
     view
    0.41
    ნ
    0.40
     ዲ
    0.39
     View
    0.38
    варти
    0.38
     lutter
    0.38
     управление
    0.38
     Solver
    0.38
    ierre
    0.36
     sencillo
    0.36
    POSITIVE LOGITS
     Vincent
    0.42
     Schl
    0.38
    }`)
    0.38
    COMDAT
    0.36
    BERG
    0.35
     STAT
    0.35
     Maid
    0.35
     Gäste
    0.35
    FBSDKLogin
    0.35
    ōu
    0.34
    Activations Density 0.001%

    No Known Activations