© 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. 228455
    Prev
    Next
    INDEX
    Explanations

    remove or incubate

    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
    wra
    0.40
    matic
    0.40
    Anim
    0.39
    ounid
    0.38
    ま
    0.37
    leaflet
    0.37
    steal
    0.37
    capability
    0.36
    透過
    0.36
    ่าย
    0.36
    POSITIVE LOGITS
     bû
    0.52
    k
    0.52
     suced
    0.50
     estrellas
    0.50
     SDW
    0.50
     whereupon
    0.48
     receb
    0.48
     parecen
    0.48
     scum
    0.48
     Aguirre
    0.48
    Activations Density 0.001%

    No Known Activations