© 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. 154298
    Prev
    Next
    INDEX
    Explanations

    unit, handle, or, building

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

    foreign or specific words

    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
     cười
    0.58
    unku
    0.55
     当然
    0.49
     cương
    0.48
     médiocrement
    0.48
     ቦ
    0.47
    diendo
    0.47
     marvell
    0.45
     कैपिट
    0.45
    bigvee
    0.44
    POSITIVE LOGITS
     Xue
    0.57
    razia
    0.50
    外
    0.48
     snap
    0.47
     Moch
    0.46
     Recherche
    0.45
    Deze
    0.44
    ائية
    0.44
     Xiang
    0.44
     Qing
    0.44
    Activations Density 0.000%

    No Known Activations