© 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. 9223
    Prev
    Next
    INDEX
    Explanations

    figure number followed by punctuation

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

    two main blocks

    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
    )$
    0.48
    โรงแรม
    0.44
    nici
    0.43
     ricco
    0.42
    bomb
    0.42
     adına
    0.41
    ্ত
    0.41
    搜
    0.41
     ámbito
    0.40
     keterangan
    0.40
    POSITIVE LOGITS
     పూర్
    0.48
     પહેલા
    0.48
    ходят
    0.46
    zeit
    0.45
    urous
    0.45
     Chil
    0.44
     появляются
    0.44
     bolj
    0.44
    йд
    0.44
    uras
    0.44
    Activations Density 0.000%

    No Known Activations