© 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. 128528
    Prev
    Next
    INDEX
    Explanations

    felt covers, version, ahead, unit servicing

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

    quality metrics

    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
     एक्सपेरिमेंट
    0.49
    ի
    0.46
     Automotive
    0.46
     Attorneys
    0.46
     Motorsport
    0.46
     Ships
    0.45
     Attorney
    0.44
     এখনো
    0.44
    ası
    0.44
     ছুট
    0.44
    POSITIVE LOGITS
    ڑوں
    0.47
    جیت
    0.46
    다
    0.46
    radial
    0.45
    تھی
    0.44
    DEFG
    0.43
    square
    0.42
    deh
    0.42
    قر
    0.41
    diagram
    0.41
    Activations Density 0.000%

    No Known Activations