© 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. 123257
    Prev
    Next
    INDEX
    Explanations

    dates and specifics

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

    conditions and limitations

    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
    和
    0.52
     và
    0.51
     или
    0.50
    或是
    0.50
     и
    0.50
    或
    0.50
     มี
    0.49
    及
    0.49
    /
    0.48
    或者
    0.47
    POSITIVE LOGITS
     fusing
    0.44
     sandwiched
    0.43
     منجر
    0.41
     solely
    0.40
    தைத்
    0.40
     tijdens
    0.40
     interment
    0.39
     अनलॉक
    0.39
     withdrew
    0.38
     podczas
    0.38
    Activations Density 0.073%

    No Known Activations