© 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. 68816
    Prev
    Next
    INDEX
    Explanations

    box of, romantic gardens, odd number

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

    whatever, or alternatives

    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
    ↵
    0.51
    تب
    0.49
    на
    0.48
    تس
    0.47
    स्पेक्टर
    0.47
     drauf
    0.46
    ت
    0.44
     dịch
    0.44
     услу
    0.44
    电影
    0.43
    POSITIVE LOGITS
    reated
    0.51
     samostat
    0.51
     awaken
    0.48
     reconstructing
    0.47
     segregation
    0.47
     rebuilding
    0.46
     nationality
    0.46
     reconst
    0.46
     わ
    0.46
    awed
    0.46
    Activations Density 0.004%

    No Known Activations