© 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. 15990
    Prev
    Next
    INDEX
    Explanations

    questions and lists

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

    lists of different languages

    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
    8
    0.30
    0
    0.29
    6
    0.26
    জন্য
    0.25
     chord
    0.24
    weapp
    0.24
    is
    0.24
     was
    0.24
    9
    0.24
     corpus
    0.24
    POSITIVE LOGITS
     และ
    0.34
     등의
    0.32
     등을
    0.31
     เช่น
    0.31
     போன்றவற்ற
    0.30
     등으로
    0.29
    地说
    0.29
    、
    0.29
     इत्यादि
    0.29
     다양한
    0.28
    Activations Density 0.005%

    No Known Activations