© 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. 244977
    Prev
    Next
    INDEX
    Explanations

    geographical locations and specific identifiers

    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
    mě
    0.49
     প্রেসক্লা
    0.48
     욕
    0.48
    lossen
    0.45
     stoichi
    0.45
    ľov
    0.43
     sorts
    0.43
     букме
    0.43
     పంట
    0.42
     interessiert
    0.42
    POSITIVE LOGITS
     ntawm
    0.48
    为
    0.46
     dengan
    0.44
     European
    0.44
     Scottish
    0.43
    ोच्च
    0.43
    વતી
    0.42
    ່ງ
    0.41
    وی
    0.41
     membaca
    0.41
    Activations Density 0.000%

    No Known Activations