© 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. 200408
    Prev
    Next
    INDEX
    Explanations

    dipping sauce, slot canyon, measure, HSE

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

    relationships and emotions

    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
    டிக்க
    0.49
    MONT
    0.48
     pharmaceuticals
    0.47
     fortes
    0.45
    संपादन
    0.45
    لی
    0.44
    锑
    0.44
     nutrients
    0.44
    ﺩ
    0.44
    잿
    0.44
    POSITIVE LOGITS
    mutex
    0.46
     компенса
    0.46
     કુલ
    0.45
     mitigated
    0.45
    <0xBE>
    0.44
     possibile
    0.43
    កម្ម
    0.43
     retras
    0.43
     পুরস্কার
    0.43
    không
    0.42
    Activations Density 0.001%

    No Known Activations