© 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. 96089
    Prev
    Next
    INDEX
    Explanations

    cryptococcus infection stages controller ASP

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

    list equals or followed by list

    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
     chars
    0.50
    ?
    0.50
     lapar
    0.46
     Nisan
    0.46
     spectre
    0.46
     spect
    0.45
    きましたが
    0.45
     uk
    0.44
     wnios
    0.44
    ;
    0.43
    POSITIVE LOGITS
    cra
    0.55
     Blogging
    0.52
     Bonding
    0.50
    cier
    0.48
    孬
    0.44
    胜
    0.43
    呿
    0.43
    辈子
    0.43
     déchets
    0.42
     Acá
    0.41
    Activations Density 0.001%

    No Known Activations