© 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. 134189
    Prev
    Next
    INDEX
    Explanations

    foreign and english words

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

    technical terms

    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
     documented
    0.51
    嚣
    0.47
     aggravated
    0.46
    otrexate
    0.45
    pe
    0.45
     misspelled
    0.45
    ಡಿದ
    0.45
     unbelievable
    0.45
     comforting
    0.44
    ays
    0.44
    POSITIVE LOGITS
    各自
    0.52
    รอบ
    0.49
     régions
    0.47
    阃
    0.46
     își
    0.46
    不受
    0.45
     Niederlande
    0.45
    侦
    0.44
    的网络
    0.44
     फोर्स
    0.44
    Activations Density 0.000%

    No Known Activations