© 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. 117362
    Prev
    Next
    INDEX
    Explanations

    contact lawyers

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

    common phrases and their continuations

    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
    苏联
    0.55
     उपनिवेश
    0.51
    molecular
    0.49
     इम्यून
    0.48
     فلسط
    0.47
    podob
    0.46
     약
    0.44
    やっぱり
    0.43
     수행
    0.42
     ე
    0.42
    POSITIVE LOGITS
     rivers
    0.47
     chhoti
    0.47
     valleys
    0.47
     Ramesh
    0.47
    कारों
    0.45
     vans
    0.45
     Kishore
    0.44
     casings
    0.44
    ঝো
    0.44
     fitter
    0.44
    Activations Density 0.000%

    No Known Activations