© 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. 172600
    Prev
    Next
    INDEX
    Explanations

    wing commanderseek Him earnestlyextract gold from motherboards

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

    explaining options

    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
    Create
    0.51
     Infectious
    0.49
    underscore
    0.49
     Moż
    0.47
    creat
    0.47
    States
    0.46
    Suppress
    0.46
    )[[
    0.46
     உருவாக்க
    0.45
    accompl
    0.45
    POSITIVE LOGITS
    菈
    0.50
    ྪ
    0.46
     propietario
    0.45
    ୌ
    0.45
    ק
    0.45
    ла
    0.45
     desal
    0.44
    ᵔ
    0.44
    િક
    0.43
    财
    0.42
    Activations Density 0.001%

    No Known Activations