© 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. 112639
    Prev
    Next
    INDEX
    Explanations

    carrier, award, canvas, weekend

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

    sunrise paints or cracks

    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
     teeming
    0.55
     વર્ષ
    0.54
     நிமிட
    0.53
    ượu
    0.52
     약
    0.52
     선택
    0.51
     Реа
    0.50
    日下午
    0.49
     어디
    0.49
     જીવન
    0.49
    POSITIVE LOGITS
    ستوى
    0.45
     hame
    0.42
    榄
    0.42
    או
    0.41
    م
    0.40
     jod
    0.40
    elé
    0.39
    ковский
    0.39
    סה
    0.39
    بلو
    0.39
    Activations Density 0.000%

    No Known Activations