© 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. 249202
    Prev
    Next
    INDEX
    Explanations

    most common

    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
     Bridge
    0.51
    ולם
    0.47
     Mage
    0.46
     Searches
    0.45
     Flies
    0.44
    煖
    0.44
    भाग्य
    0.44
     ofici
    0.44
    葢
    0.44
     Mechanics
    0.43
    POSITIVE LOGITS
     کی۔
    0.47
    fj
    0.46
    MatContext
    0.46
     প্রে
    0.45
     milliard
    0.45
     تھے۔
    0.44
     inneh
    0.43
    avamo
    0.43
    。\
    0.42
     அவற்றில்
    0.42
    Activations Density 0.000%

    No Known Activations