© 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. 105488
    Prev
    Next
    INDEX
    Explanations

    better, best, gone, daily

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

    helpful if

    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
     comidas
    0.53
    佛
    0.51
     comida
    0.50
    ǀ
    0.49
    )}+\
    0.49
    母親
    0.48
    }+\
    0.48
     abusers
    0.47
    玼
    0.46
    雅
    0.45
    POSITIVE LOGITS
     коллеги
    0.49
     Schatten
    0.46
     خیر
    0.46
    зий
    0.45
     شہر
    0.44
     проєкту
    0.44
    जेंडर
    0.44
     reincarn
    0.44
    зите
    0.44
    ່ານ
    0.43
    Activations Density 0.000%

    No Known Activations