© 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. 237823
    Prev
    Next
    INDEX
    Explanations

    what we present

    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
     hra
    0.52
     mappa
    0.49
    ,
    0.47
    -
    0.46
    ดิน
    0.46
     mapp
    0.46
     cull
    0.46
    :
    0.46
    Domain
    0.45
     Habsburg
    0.44
    POSITIVE LOGITS
    opholes
    0.48
     modificaciones
    0.48
    쫌
    0.46
    spun
    0.46
    copies
    0.46
    😒
    0.45
     realice
    0.45
    deo
    0.44
    uciones
    0.44
    یعنی
    0.44
    Activations Density 0.000%

    No Known Activations