© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83722
    Prev
    Next
    INDEX
    Explanations

    handle, designed, battery, trailer, gallon

    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_31_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
     coer
    0.47
     desigualdad
    0.46
     fascin
    0.43
     sobren
    0.43
    狀
    0.42
    antiate
    0.42
     disagrees
    0.41
    ্টি
    0.40
     cerr
    0.40
     desigual
    0.40
    POSITIVE LOGITS
    s
    0.72
     eller
    0.46
     PowerShell
    0.45
    ים
    0.45
     cry
    0.44
    epad
    0.44
     meatballs
    0.44
     install
    0.43
    реза
    0.43
    Ꮡ
    0.43
    Activations Density 0.001%

    No Known Activations