© 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. 22373
    Prev
    Next
    INDEX
    Explanations

    ways to

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

    cannot and will not

    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
     mesmas
    0.36
     njima
    0.36
    гим
    0.35
    дер
    0.35
     lainnya
    0.35
    걔
    0.35
    悽
    0.34
     largos
    0.33
    ฟ
    0.33
    性感
    0.33
    POSITIVE LOGITS
    များသည်
    0.39
     தமிழக
    0.32
     ئەو
    0.32
     Hertfordshire
    0.32
     Colchester
    0.32
     مدينة
    0.32
     যুক্তরাজ্যের
    0.32
    咗
    0.30
     Britain
    0.30
     τὰ
    0.30
    Activations Density 0.176%

    No Known Activations