© 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. 195468
    Prev
    Next
    INDEX
    Explanations

    with our or he sets

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

    `Its` descriptive phrases

    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
    de
    0.46
    exitTool
    0.46
     ingat
    0.45
     ê
    0.44
    équipe
    0.42
     était
    0.41
     iš
    0.41
    gia
    0.41
    ê
    0.41
     opérateur
    0.40
    POSITIVE LOGITS
    ത്തിറ
    0.49
    俊
    0.43
     কিভাবে
    0.42
     Precio
    0.41
     Neust
    0.41
     Го
    0.41
    ु
    0.41
     Pollock
    0.40
     구할
    0.40
    rard
    0.39
    Activations Density 0.000%

    No Known Activations