© 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. 89739
    Prev
    Next
    INDEX
    Explanations

    spray foam, saving money, legal requirements

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

    strategies for improvement

    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
    riften
    0.51
     RIS
    0.50
    ertian
    0.50
     résidence
    0.46
    ैनिक
    0.46
    ="...">
    0.46
    finement
    0.44
     récomp
    0.44
    rib
    0.43
    itió
    0.43
    POSITIVE LOGITS
     ڈیٹا
    0.50
    Quanto
    0.49
    وڈ
    0.47
    疸
    0.46
     angiogenic
    0.45
     bevorzug
    0.45
     தீங்கு
    0.44
    суз
    0.44
     शेवट
    0.43
     Shir
    0.43
    Activations Density 0.001%

    No Known Activations