© 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. 240301
    Prev
    Next
    INDEX
    Explanations

    hospitality or dining service

    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
     OSA
    0.52
    狩
    0.43
     энер
    0.43
     PNG
    0.42
     уста
    0.41
    댐
    0.41
    罘
    0.41
     エネルギー
    0.41
     cl
    0.40
    nge
    0.40
    POSITIVE LOGITS
     straks
    0.46
    Waiter
    0.46
    瀛
    0.44
     Dine
    0.44
     gestire
    0.44
    Couple
    0.42
    EJ
    0.41
     Geh
    0.41
    Dining
    0.40
    Excuse
    0.40
    Activations Density 0.001%

    No Known Activations