© 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. 204515
    Prev
    Next
    INDEX
    Explanations

    stellar mass

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

    middle element or definition

    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
     خات
    0.40
     τρο
    0.40
     私
    0.39
     sapphire
    0.39
    瞬间
    0.39
     crocodile
    0.38
     жаңы
    0.37
    妠
    0.37
    .\\
    0.37
     anillos
    0.36
    POSITIVE LOGITS
    boards
    0.44
    develop
    0.44
    早就
    0.44
    ۵
    0.42
    programming
    0.40
    mason
    0.40
    histoire
    0.40
    ol
    0.40
     feudal
    0.40
    hundred
    0.40
    Activations Density 0.001%

    No Known Activations