© 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. 67008
    Prev
    Next
    INDEX
    Explanations

    religious and inquiring contexts

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

    describing impacts and conditions

    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
    Election
    0.49
     आपदा
    0.49
    चुनाव
    0.46
    Houses
    0.45
    у
    0.45
    ле
    0.45
     election
    0.45
    คุณ
    0.44
    нд
    0.43
     Election
    0.42
    POSITIVE LOGITS
    èbre
    0.46
    ciò
    0.46
     expressão
    0.45
     转
    0.45
    asă
    0.44
     மணிக்கு
    0.44
    ković
    0.43
     setae
    0.43
     accessoires
    0.43
     insanın
    0.43
    Activations Density 0.001%

    No Known Activations