© 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. 64554
    Prev
    Next
    INDEX
    Explanations

    mixed foreign language and specific terms

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

    stores information

    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
    '
    0.54
    μμα
    0.48
    Score
    0.48
    alyse
    0.47
    achtet
    0.47
    اكم
    0.47
    Router
    0.47
    Procedure
    0.46
    基
    0.46
    এই
    0.45
    POSITIVE LOGITS
     demonic
    0.55
     Apostolic
    0.50
     آہستہ
    0.48
     Jepang
    0.46
     japon
    0.46
     giapp
    0.46
     granddaughters
    0.46
    ylmethylsulfanyl
    0.46
     일본
    0.46
    apayati
    0.45
    Activations Density 0.001%

    No Known Activations