© 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. 14303
    Prev
    Next
    INDEX
    Explanations

    foreign languages and scientific text

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

    covering genomes and genetic information

    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
     څه
    0.45
    ᱪ
    0.44
    況
    0.41
    وڑا
    0.40
    說
    0.40
    dictionary
    0.40
    িও
    0.40
    を選ぶ
    0.40
    用紙
    0.40
    এছাড়া
    0.39
    POSITIVE LOGITS
     kanggo
    0.57
     zwią
    0.50
     goût
    0.50
    ımıza
    0.48
    ).</
    0.47
     comte
    0.46
     për
    0.46
     médioc
    0.46
    któ
    0.45
     gehörte
    0.45
    Activations Density 0.000%

    No Known Activations