© 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. 12206
    Prev
    Next
    INDEX
    Explanations

    early as

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

    off-the-beaten-path experiences

    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
     milit
    0.46
    란
    0.45
     Veracruz
    0.44
     Milit
    0.44
     Wonderland
    0.43
    chus
    0.43
     Blas
    0.43
     disorganized
    0.42
     reten
    0.42
     feud
    0.42
    POSITIVE LOGITS
    শ্ত
    0.56
     কাজকর্ম
    0.51
    arbeitet
    0.47
    Pyro
    0.47
    
    0.46
     PROJECTS
    0.46
     scuola
    0.46
    ﾍ
    0.46
    淍
    0.46
     আসবে
    0.45
    Activations Density 0.000%

    No Known Activations