© 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. 35266
    Prev
    Next
    INDEX
    Explanations

    certain/some/notable/reportedly

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

    certain / some languages

    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
     vreau
    0.54
     Итак
    0.52
     empezamos
    0.47
     istedi
    0.47
     devemos
    0.46
     iniziamo
    0.45
     kuiten
    0.45
     ();
    0.45
    所以我
    0.44
    ั้น
    0.43
    POSITIVE LOGITS
     некоторых
    0.51
     Certains
    0.50
     certains
    0.49
    据说
    0.49
    }}
    0.49
    Notable
    0.48
     niektórych
    0.47
    }
    0.47
     برخی
    0.46
     некоторые
    0.46
    Activations Density 0.009%

    No Known Activations