© 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. 203681
    Prev
    Next
    INDEX
    Explanations

    offered by, seals off, potential home, wished to

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

    non-English 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
    es
    0.64
    opa
    0.55
    in
    0.48
    os
    0.47
    era
    0.46
    igenes
    0.46
    自
    0.46
    FA
    0.45
    erry
    0.45
    ecas
    0.44
    POSITIVE LOGITS
     giống
    0.57
     trại
    0.54
     obiekt
    0.53
     ἢ
    0.52
     વિકાસ
    0.52
     vudd
    0.52
     đình
    0.52
     vibhav
    0.52
     STRAIGHT
    0.50
     विराम
    0.50
    Activations Density 0.001%

    No Known Activations