© 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. 37067
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    numbers represents ASCII codes

    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
     судо
    0.46
    ։
    0.45
     supernatants
    0.44
     ਜਾਂ
    0.42
     ।
    0.42
    aping
    0.41
     проце
    0.41
    hen
    0.40
     چھ
    0.39
    mary
    0.39
    POSITIVE LOGITS
    يمان
    0.55
     promesa
    0.51
     wissen
    0.48
     preciso
    0.48
     mencionar
    0.48
    ก
    0.47
     Bé
    0.46
    دأ
    0.46
    തേ
    0.46
     decirlo
    0.46
    Activations Density 0.000%

    No Known Activations