© 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. 127644
    Prev
    Next
    INDEX
    Explanations

    Gala Auction

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

    conditions, expansion, prompts

    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
     ventilation
    0.49
     density
    0.45
     raw
    0.45
     percentage
    0.44
     deviated
    0.44
     verified
    0.44
     septic
    0.44
     (
    0.43
     installed
    0.43
     check
    0.43
    POSITIVE LOGITS
    ovatel
    0.56
    áře
    0.55
    égek
    0.55
    ități
    0.54
     empresas
    0.52
    óż
    0.52
    ρους
    0.52
    autor
    0.52
    ським
    0.52
    átu
    0.51
    Activations Density 0.000%

    No Known Activations