© 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. 84411
    Prev
    Next
    INDEX
    Explanations

    numbers and specific phrases

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

    algorithms identify patterns

    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
     que
    0.54
     that
    0.50
    。
    0.50
    ’
    0.49
     targeting
    0.49
     grading
    0.48
    å
    0.47
     B
    0.46
    я
    0.46
     lena
    0.46
    POSITIVE LOGITS
    жкой
    0.56
    moniker
    0.55
    مانی
    0.52
     علت
    0.51
    jegyz
    0.51
    })$;
    0.50
    recomend
    0.50
    铯
    0.50
    拁
    0.50
    usermodel
    0.50
    Activations Density 0.000%

    No Known Activations