© 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. 124276
    Prev
    Next
    INDEX
    Explanations

    item attributes and types

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

    descriptive terms for labels

    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
    6
    0.49
    5
    0.48
     has
    0.47
     is
    0.46
     are
    0.46
    たちが
    0.45
    7
    0.44
    4
    0.44
     teraz
    0.44
    accessories
    0.43
    POSITIVE LOGITS
    ۔
    0.43
    kovskij
    0.40
     данный
    0.40
    agamanam
    0.40
    |।
    0.40
    pInBuffer
    0.40
    喤
    0.40
    ্ত্র
    0.40
    ্তন
    0.39
    ።
    0.39
    Activations Density 0.001%

    No Known Activations