© 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. 139587
    Prev
    Next
    INDEX
    Explanations

    later / sequence

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

    customer service

    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
     약
    0.48
     DOCUMENT
    0.42
    bentuk
    0.42
     데이터를
    0.42
     الدر
    0.41
     무게
    0.41
    west
    0.41
    ığın
    0.41
     ขั้น
    0.41
    western
    0.40
    POSITIVE LOGITS
    াবু
    0.52
    丏
    0.50
    ેચ્છ
    0.49
    Classes
    0.47
     Editions
    0.46
     kasnije
    0.46
     Idris
    0.46
     senere
    0.45
    遄
    0.45
     later
    0.45
    Activations Density 0.001%

    No Known Activations