© 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. 239563
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
    to
    0.50
    handlungen
    0.49
     ከመ
    0.48
    唓
    0.48
    穩定
    0.47
    of
    0.47
    ᱙
    0.47
    約
    0.46
    track
    0.46
    monotonic
    0.46
    POSITIVE LOGITS
    OU
    0.48
     frances
    0.48
     debemos
    0.48
     нужно
    0.48
     kabar
    0.47
     progett
    0.47
     achar
    0.47
     treba
    0.47
     потрібно
    0.47
     gương
    0.46
    Activations Density 0.000%

    No Known Activations