© 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. 130630
    Prev
    Next
    INDEX
    Explanations

    wealth, companies, competitiveness, newsletters

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

    code formatting and punctuation

    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
    chants
    0.52
    }$.
    0.51
    ب
    0.51
    section
    0.50
    globin
    0.50
    в
    0.50
    й
    0.49
    ле
    0.48
    ill
    0.47
    R
    0.47
    POSITIVE LOGITS
     kry
    0.51
     Krzysz
    0.48
     Brownian
    0.46
     Sasha
    0.46
     जाम
    0.46
     JAM
    0.46
     চিঠি
    0.45
     założ
    0.45
     bear
    0.44
     Attic
    0.44
    Activations Density 0.000%

    No Known Activations