© 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. 109004
    Prev
    Next
    INDEX
    Explanations

    change, transformation, alteration

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

    explaining why

    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
    א
    0.48
    า
    0.47
     écrire
    0.47
     parâmetros
    0.46
    烨
    0.46
    人數
    0.46
     قائ
    0.46
    बांग
    0.46
    ംഗ്
    0.45
     connecter
    0.45
    POSITIVE LOGITS
    i
    0.57
    changed
    0.57
    change
    0.50
    turned
    0.50
    u
    0.50
    changes
    0.49
    goods
    0.49
    washed
    0.48
    ine
    0.48
     changed
    0.48
    Activations Density 0.000%

    No Known Activations