© 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. 164540
    Prev
    Next
    INDEX
    Explanations

    comprehensive maintenance

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

    biometrics, directories, governance, reliable

    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
     chipped
    0.50
    рая
    0.45
     conspicuously
    0.45
    し
    0.45
     petróleo
    0.44
     mohou
    0.44
     bericht
    0.44
    EX
    0.44
    ДС
    0.44
    췄
    0.44
    POSITIVE LOGITS
     Chag
    0.48
    Authenticator
    0.47
     Datenbank
    0.46
     મત
    0.46
    imantan
    0.46
     Albu
    0.46
     FAL
    0.46
     Alcal
    0.45
     Mojave
    0.44
     Fal
    0.44
    Activations Density 0.000%

    No Known Activations