© 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. 75142
    Prev
    Next
    INDEX
    Explanations

    specific examples

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

    explain how concepts relate

    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
    ;
    0.49
     expenditures
    0.47
     Apesar
    0.45
     após
    0.45
     MULT
    0.44
     disfruta
    0.44
     despite
    0.43
     Después
    0.43
     Despite
    0.42
     அனை
    0.42
    POSITIVE LOGITS
    JVM
    0.45
    Colon
    0.42
    协
    0.42
     державної
    0.40
    Primitive
    0.39
    relse
    0.39
     સમજ
    0.39
    বিল
    0.39
     ବି
    0.39
    жной
    0.39
    Activations Density 0.000%

    No Known Activations