© 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. 59773
    Prev
    Next
    INDEX
    Explanations

    volume or issue numbers

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

    actions, security, and technical terms

    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
    ا
    0.57
    ки
    0.50
     দ্বারা
    0.49
    ı
    0.46
    தால்
    0.45
    кина
    0.44
    ため
    0.44
    к
    0.44
    のみ
    0.43
     बँ
    0.43
    POSITIVE LOGITS
     sharpen
    0.47
     glaring
    0.46
     뉴스
    0.45
    客户端
    0.44
     antivirus
    0.43
     xray
    0.43
     IMAGE
    0.43
     rss
    0.43
     poput
    0.43
     dropbox
    0.43
    Activations Density 0.000%

    No Known Activations