© 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. 117307
    Prev
    Next
    INDEX
    Explanations

    expansion valve

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

    shell scripting

    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
    πομπ
    0.47
    Vinyl
    0.46
    читы
    0.45
    Lil
    0.45
    ফ
    0.43
    ละคร
    0.43
    ឱ្យ
    0.43
    んな
    0.42
    돛
    0.42
    Roots
    0.42
    POSITIVE LOGITS
     virulent
    0.50
     Francia
    0.50
     flexibilidad
    0.50
     fase
    0.50
     Presidente
    0.50
     Influenza
    0.49
     riduzione
    0.48
     Alemania
    0.47
     nella
    0.47
     generación
    0.46
    Activations Density 0.000%

    No Known Activations