© 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. 248435
    Prev
    Next
    INDEX
    Explanations

    Careers and calamities

    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
    深受
    0.41
    encountered
    0.38
    द्वारा
    0.38
     পায়নি
    0.38
     गाइड
    0.38
     হরি
    0.37
    재
    0.36
     پنجاب
    0.36
     коммуна
    0.36
    期待
    0.35
    POSITIVE LOGITS
    í
    0.48
    因为它
    0.47
    ace
    0.46
    ní
    0.46
    ci
    0.45
    because
    0.45
    scriptsize
    0.44
    issante
    0.44
    ισ
    0.43
     цих
    0.43
    Activations Density 0.001%

    No Known Activations