© 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. 39657
    Prev
    Next
    INDEX
    Explanations

    food description and related amenities

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

    fold flat, sweet and/or or, Citizens and, could try/say, Cold Feet

    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
     erstwhile
    0.47
    之所以
    0.39
    ᄌ
    0.38
     dynasties
    0.38
    ವಾದ
    0.37
    猙
    0.37
    entities
    0.36
    ði
    0.36
    FBSDKLogin
    0.35
    osphere
    0.35
    POSITIVE LOGITS
     تناول
    0.39
     හෝ
    0.38
    折
    0.38
     подобных
    0.38
     সরকারী
    0.38
     做
    0.38
     জরুরী
    0.37
     بیرون
    0.37
    జె
    0.37
    姻
    0.37
    Activations Density 0.000%

    No Known Activations