© 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. 217250
    Prev
    Next
    INDEX
    Explanations

    date placement

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

    I am, I'm, I don't

    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
     vaporization
    0.55
     рассказа
    0.54
     aggravating
    0.51
     odor
    0.47
     ρ
    0.47
     knot
    0.46
     آب
    0.46
     militia
    0.45
     vapors
    0.45
    جب
    0.45
    POSITIVE LOGITS
    odigd
    0.51
    i
    0.50
    는
    0.50
    éditeur
    0.47
    蘇
    0.46
    า
    0.46
    Bep
    0.45
    Implement
    0.44
    zentrum
    0.44
    e
    0.44
    Activations Density 0.001%

    No Known Activations