© 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. 189912
    Prev
    Next
    INDEX
    Explanations

    invitation for animals

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

    compress incoming, create shades

    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
     caoutch
    0.54
     imperme
    0.54
     hydrogens
    0.52
     fluoro
    0.52
     divergents
    0.51
     membrana
    0.51
    яд
    0.51
    $-$,
    0.50
     histidine
    0.50
     aluminium
    0.49
    POSITIVE LOGITS
    ella
    0.51
    )
    0.47
     Pub
    0.45
    ro
    0.44
    ena
    0.42
    encar
    0.42
     Sheraton
    0.42
    queline
    0.41
     Birk
    0.41
    ede
    0.41
    Activations Density 0.000%

    No Known Activations