© 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. 53699
    Prev
    Next
    INDEX
    Explanations

    author, artist, director

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

    capturing local texture

    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
     grows
    0.45
    )))))
    0.45
     রাষ্ট্রের
    0.44
     ਪਰ
    0.43
    )!
    0.43
    SL
    0.42
     Slater
    0.42
    ろ
    0.41
    母親
    0.41
     joy
    0.41
    POSITIVE LOGITS
     Brush
    0.47
    ꔹ
    0.47
    aise
    0.45
    arranty
    0.45
    伍
    0.45
    क्रीम
    0.43
    觊
    0.43
    给
    0.42
    bonne
    0.41
    र्यंत
    0.41
    Activations Density 0.000%

    No Known Activations