© 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. 138917
    Prev
    Next
    INDEX
    Explanations

    location and relation words

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

    specific word definitions

    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
    ائو
    0.38
     blant
    0.37
     Ranc
    0.36
     ImageData
    0.35
     â
    0.35
     السنوات
    0.35
    <0x9B>
    0.34
     pas
    0.33
    â
    0.33
     minute
    0.33
    POSITIVE LOGITS
     thereof
    0.85
     therein
    0.79
     therefrom
    0.63
     thereunder
    0.61
    在那里
    0.61
     उसमें
    0.60
     dort
    0.59
    その
    0.57
     উহা
    0.57
     সেখানেই
    0.56
    Activations Density 0.355%

    No Known Activations