© 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. 233651
    Prev
    Next
    INDEX
    Explanations

    Dear Editor

    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
    genuine
    0.46
    vál
    0.44
     Stations
    0.43
    ización
    0.43
     ㅜ
    0.41
     Charitable
    0.39
    🄴
    0.39
    CLES
    0.39
    ********/
    0.38
    ierry
    0.38
    POSITIVE LOGITS
     macrophage
    0.52
     ಅವರನ್ನು
    0.46
     hypoth
    0.45
    তাদের
    0.45
     predation
    0.45
     raggiungere
    0.44
     synth
    0.44
     ಅವರ
    0.44
     deforestation
    0.43
     mediated
    0.43
    Activations Density 0.003%

    No Known Activations