© 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. 139403
    Prev
    Next
    INDEX
    Explanations

    availablestatesmagnitudeoneshared

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

    keywords and actions

    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
     diskut
    0.51
    K
    0.49
     angesch
    0.48
     dů
    0.48
    。《
    0.47
     erklärt
    0.46
    Rés
    0.45
    وسي
    0.45
     banker
    0.45
     milj
    0.44
    POSITIVE LOGITS
    みが
    0.45
    द्वितीय
    0.44
    ｺ
    0.44
     जिसे
    0.43
     آق
    0.42
     教え
    0.42
     объектов
    0.41
     собственные
    0.41
    愘
    0.41
     नान
    0.41
    Activations Density 0.000%

    No Known Activations