© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 184400
    Prev
    Next
    INDEX
    Explanations

    lists, phrases, or collections

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

    keylogger program or code

    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
     Rs
    0.48
     Also
    0.46
     will
    0.44
     Todo
    0.43
     I
    0.43
     All
    0.42
     imediat
    0.42
    还是很
    0.42
     We
    0.41
     Ensure
    0.41
    POSITIVE LOGITS
    ώσει
    0.46
    󠁢
    0.45
     fondée
    0.45
     compatriots
    0.45
     collectivités
    0.44
     законодав
    0.44
     therapeutics
    0.43
     ondernem
    0.42
     മനുഷ്യ
    0.42
     університе
    0.41
    Activations Density 0.001%

    No Known Activations