© 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. 8922
    Prev
    Next
    INDEX
    Explanations

    from the

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

    even conservative

    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
    னுக்கு
    0.47
     berita
    0.46
     n
    0.44
     август
    0.43
    DeleteDialogOpen
    0.42
     tudi
    0.42
     muhimu
    0.42
    時には
    0.42
     puncak
    0.42
     രാജ
    0.42
    POSITIVE LOGITS
     elems
    0.56
     surfactants
    0.51
    ㅛ
    0.47
     workmanship
    0.46
    kult
    0.46
     Instrum
    0.45
    ₂(
    0.43
    віч
    0.43
     Ornamental
    0.43
    bted
    0.43
    Activations Density 0.000%

    No Known Activations