© 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. 239099
    Prev
    Next
    INDEX
    Explanations

    inquiry, person, education, online

    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
    ورا
    0.52
    تباين
    0.50
    ոտ
    0.50
    سمى
    0.50
    يين
    0.47
    ي
    0.47
    يب
    0.46
    ores
    0.45
    عي
    0.45
    غال
    0.45
    POSITIVE LOGITS
     ながら
    0.52
     だっ
    0.48
     conf
    0.46
     だ
    0.45
     プロ
    0.44
     שמ
    0.44
     가까
    0.44
     compet
    0.42
     disse
    0.42
     concl
    0.42
    Activations Density 0.000%

    No Known Activations