© 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. 238406
    Prev
    Next
    INDEX
    Explanations

    words and phrases

    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
     Seite
    0.52
    för
    0.52
    teilung
    0.50
     Abteilung
    0.50
    摁
    0.50
     Figur
    0.49
     Filme
    0.48
     stella
    0.47
     Illuminate
    0.46
     Stell
    0.46
    POSITIVE LOGITS
    AKT
    0.50
    ED
    0.48
     forces
    0.46
    =\
    0.45
    COc
    0.43
    consumers
    0.42
    ТС
    0.42
    лекет
    0.42
    miR
    0.42
     tri
    0.42
    Activations Density 0.001%

    No Known Activations