© 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. 189239
    Prev
    Next
    INDEX
    Explanations

    instructions, then take, selected by, laughed about

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

    precedents and reliability rules

    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
     то
    0.50
     réfl
    0.50
     έγινε
    0.47
     передба
    0.47
     இணைந்து
    0.46
     GDPPC
    0.46
    <0x80>
    0.45
    த்துறை
    0.45
     Η
    0.45
    LE
    0.44
    POSITIVE LOGITS
     barrier
    0.45
     bato
    0.45
     hyperlink
    0.44
     davvero
    0.43
     facebook
    0.42
     బ్రి
    0.42
     baller
    0.42
     bolt
    0.42
     honda
    0.42
     nj
    0.41
    Activations Density 0.001%

    No Known Activations