© 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. 99615
    Prev
    Next
    INDEX
    Explanations

    sequences of actions or states

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

    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
    に取り組
    0.49
    ด
    0.48
     모
    0.47
    坂
    0.47
    🔇
    0.47
    Sac
    0.46
    )，
    0.46
    드
    0.45
    メカ
    0.45
     등의
    0.45
    POSITIVE LOGITS
     রাত
    0.46
     respirator
    0.46
     capitán
    0.45
     Redirect
    0.43
     kopi
    0.43
     Ryanair
    0.43
    ker
    0.42
    wall
    0.42
     Geschäftsführer
    0.41
     Ikat
    0.41
    Activations Density 0.001%

    No Known Activations