© 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. 164629
    Prev
    Next
    INDEX
    Explanations

    asked about anyone

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

    sarcasm, hydration, catching, email addresses

    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
    ’
    0.64
    '
    0.62
     of
    0.46
    ).
    0.46
     Preliminary
    0.45
    Palette
    0.44
    。
    0.44
    </em>
    0.44
    CT
    0.44
    OfString
    0.43
    POSITIVE LOGITS
    <unused27>
    0.59
     nuestros
    0.59
    ನನ್ನು
    0.59
     nossos
    0.58
     ಕಡಿಮೆ
    0.56
    ൧
    0.55
     کم
    0.54
     especialistas
    0.54
     சரா
    0.54
    सेवक
    0.53
    Activations Density 0.001%

    No Known Activations