© 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. 203698
    Prev
    Next
    INDEX
    Explanations

    ATM machines

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

    Facebook Got

    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
     urządzenia
    0.53
     pô
    0.52
     punctured
    0.47
     t
    0.47
    訊
    0.46
    𝒹
    0.44
     Ztg
    0.44
     pozdě
    0.43
    దన
    0.43
     $\
    0.43
    POSITIVE LOGITS
    फारिश
    0.50
    اعه
    0.48
    Boat
    0.47
    eller
    0.46
    Lopez
    0.46
    airplane
    0.44
     комплекс
    0.44
     விமான
    0.44
     ইন্ডি
    0.44
    圩
    0.44
    Activations Density 0.001%

    No Known Activations