© 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. 201444
    Prev
    Next
    INDEX
    Explanations

    titles and names

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

    foreign language text

    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
     eSIM
    0.50
     eCommerce
    0.49
     Envi
    0.47
     Vermeer
    0.46
     Hartree
    0.45
     LiDAR
    0.45
    🫧
    0.45
    📈
    0.44
     Groundwater
    0.44
     Vince
    0.44
    POSITIVE LOGITS
     मोहम्मद
    0.48
     अफगानिस्तान
    0.46
    grupo
    0.46
     जानेवारी
    0.46
     Australie
    0.46
     asimismo
    0.45
    ーストラリア
    0.45
    quiao
    0.45
    apons
    0.44
     altres
    0.43
    Activations Density 0.001%

    No Known Activations