© 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. 64539
    Prev
    Next
    INDEX
    Explanations

    multiple languages, nationalities

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

    communicate in Chinese

    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
     GUAR
    0.47
     OVA
    0.45
     OSX
    0.44
    곶
    0.44
     prover
    0.43
     Qf
    0.43
     Guaranteed
    0.43
     pulm
    0.43
     PASS
    0.43
     Changed
    0.43
    POSITIVE LOGITS
     countrymen
    0.53
    人々
    0.47
     словами
    0.45
     подвод
    0.45
     نیشنل
    0.45
    uts
    0.45
     aggress
    0.44
    ٩
    0.44
     اکنون
    0.43
    国の
    0.43
    Activations Density 0.000%

    No Known Activations