© 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. 257601
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ٹ
    0.46
    మే
    0.43
    辔
    0.42
     vipp
    0.41
    ٹنگ
    0.39
    uiar
    0.39
    债
    0.38
     চ্যানেল
    0.38
    愎
    0.38
     Tracks
    0.38
    POSITIVE LOGITS
    PRINT
    0.45
     городе
    0.44
     город
    0.41
    &=\
    0.39
    LETIN
    0.39
    SPEED
    0.38
    getUsername
    0.38
     शहर
    0.38
    ওয়াল
    0.38
     परिणाम
    0.38
    Activations Density 0.001%

    No Known Activations