© 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. 247439
    Prev
    Next
    INDEX
    Explanations

    ashley, other human, techniques excite, SiO2, weathertech, sold, Showa

    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
     donor
    0.46
    об
    0.45
    It
    0.43
    ет
    0.43
     الدهون
    0.43
    upport
    0.43
    stic
    0.42
    很
    0.42
    model
    0.41
     resource
    0.41
    POSITIVE LOGITS
     Regent
    0.48
     Gare
    0.47
     Buda
    0.47
     Became
    0.46
     Viitattu
    0.45
     Cinnamon
    0.45
     Bend
    0.45
     Milano
    0.44
     Rancho
    0.44
     başladı
    0.44
    Activations Density 0.000%

    No Known Activations