© 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. 151640
    Prev
    Next
    INDEX
    Explanations

    clear of, review, explorer, lead over, come here, markup, Janet, recording

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

    Tax implications, marketing services

    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
    禮
    0.55
    ᄀ
    0.52
     этих
    0.52
    ק
    0.51
    礼
    0.51
    писки
    0.50
    吔
    0.49
    邋
    0.49
    ירים
    0.48
     интересных
    0.48
    POSITIVE LOGITS
     realty
    0.57
     battalion
    0.50
     summation
    0.49
     peninsula
    0.47
     woes
    0.46
     Qatar
    0.46
     sour
    0.45
     sout
    0.45
     decade
    0.45
     CMA
    0.45
    Activations Density 0.000%

    No Known Activations