© 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. 116204
    Prev
    Next
    INDEX
    Explanations

    posters, supporter, bathroom

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

    US vs. comparison

    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
     hangi
    0.56
     dhad
    0.54
     alcanzó
    0.52
     llegó
    0.51
     chhoti
    0.51
    ᱔
    0.50
     gestellt
    0.50
     kön
    0.49
     geschaffen
    0.49
    建成
    0.48
    POSITIVE LOGITS
    ู
    0.47
    不知
    0.44
    ศัก
    0.42
    featureType
    0.42
    шо
    0.42
    שים
    0.41
    רים
    0.41
    Ⓜ
    0.40
    یشه
    0.40
    ശ
    0.40
    Activations Density 0.000%

    No Known Activations