© 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. 98309
    Prev
    Next
    INDEX
    Explanations

    on average

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

    foreign language indicators

    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
     intermin
    0.48
     réforme
    0.47
    甚至
    0.46
     ministro
    0.45
     sacerd
    0.45
     paltry
    0.45
     clergyman
    0.44
     ἢ
    0.44
     ministerial
    0.44
     rhubarb
    0.42
    POSITIVE LOGITS
     Oktober
    0.54
    November
    0.52
     Teknologi
    0.47
    also
    0.46
     ankaŭ
    0.46
     also
    0.46
    también
    0.45
     també
    0.44
    kap
    0.44
    Ms
    0.44
    Activations Density 0.001%

    No Known Activations