© 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. 133767
    Prev
    Next
    INDEX
    Explanations

    additional course claim etc

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

    hire and prices

    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
     Geoffrey
    0.52
    வல்
    0.50
    繫
    0.46
    ază
    0.46
    무리
    0.45
    हरी
    0.45
     Volodymyr
    0.44
    टिल
    0.44
    पाई
    0.43
    ൂര്‍
    0.43
    POSITIVE LOGITS
    ure
    0.45
    _{
    0.45
    AYA
    0.44
     Inhibition
    0.44
     antioxidants
    0.43
     మీద
    0.42
    aya
    0.42
    ivac
    0.42
     মিসেস
    0.41
     refused
    0.41
    Activations Density 0.001%

    No Known Activations