© 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. 190554
    Prev
    Next
    INDEX
    Explanations

    own free will

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

    specialty, integration, China

    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
     ഭക്ഷ
    0.48
     предметов
    0.47
    បញ្ចូល
    0.47
     cibo
    0.46
     ܐ
    0.46
     ekonomik
    0.46
     archaic
    0.45
     reinado
    0.45
    combinant
    0.44
     Bestand
    0.44
    POSITIVE LOGITS
     waterfall
    0.50
     moulding
    0.49
    泥
    0.45
     Guns
    0.45
    Mountains
    0.44
     계획
    0.44
     molding
    0.43
    Plastic
    0.43
    还是很
    0.43
    Krishna
    0.43
    Activations Density 0.001%

    No Known Activations