© 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. 162063
    Prev
    Next
    INDEX
    Explanations

    phrase and word sequences

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

    civilización, planet, critical, overthink, BIG, must, know, Cause, alternative

    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
    к
    0.55
    ق
    0.54
    ك
    0.49
    ين
    0.48
    شة
    0.48
    ш
    0.47
    ان
    0.44
    ز
    0.44
    ش
    0.44
     التمثيل
    0.42
    POSITIVE LOGITS
     fragmentary
    0.50
    먹
    0.47
     baffling
    0.47
     nettement
    0.46
    <<
    0.46
     puzzling
    0.45
     scanners
    0.44
    DNN
    0.44
     fractured
    0.43
     acoust
    0.43
    Activations Density 0.000%

    No Known Activations