© 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. 181400
    Prev
    Next
    INDEX
    Explanations

    language specific phrases

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

    numerical counting or conditions

    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
    非常
    0.51
    よりも
    0.50
    TAK
    0.47
    中
    0.47
    CLAMP
    0.46
    僌
    0.46
    外
    0.46
    代
    0.45
    替
    0.45
    imension
    0.44
    POSITIVE LOGITS
     París
    0.49
     hayvan
    0.48
     phố
    0.47
     trovare
    0.47
     poesía
    0.45
     hear
    0.44
     admire
    0.44
     Oxide
    0.44
     congratulate
    0.43
     entertained
    0.43
    Activations Density 0.001%

    No Known Activations