© 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. 22719
    Prev
    Next
    INDEX
    Explanations

    booking accommodation

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

    Icelandic law or footprint

    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
    ரன்
    0.46
    িক
    0.44
    ิ
    0.44
    ,
    0.41
    的书
    0.41
    ני
    0.41
    Proven
    0.40
     складі
    0.40
    ク
    0.40
    르
    0.40
    POSITIVE LOGITS
     honda
    0.44
    Honda
    0.42
     varies
    0.40
     ಬಹಳ
    0.40
     depends
    0.40
     العالمين
    0.40
     receptacle
    0.39
     ತುಂಬಾ
    0.39
     জগতে
    0.39
     pulleys
    0.38
    Activations Density 0.000%

    No Known Activations