© 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. 158384
    Prev
    Next
    INDEX
    Explanations

    reviews

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

    code and observed phenomena

    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
     الاخر
    0.48
     لائ
    0.46
    I
    0.46
    тэ
    0.45
     الإن
    0.45
    asan
    0.45
     الآخر
    0.44
     大家
    0.44
    縣
    0.44
    STER
    0.44
    POSITIVE LOGITS
     pizzas
    0.48
     herds
    0.47
     chocolates
    0.46
     difficultés
    0.46
     frosting
    0.46
     glaciers
    0.45
     surplus
    0.45
    hilt
    0.45
     ponsel
    0.44
     solaire
    0.43
    Activations Density 0.001%

    No Known Activations