© 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. 67617
    Prev
    Next
    INDEX
    Explanations

    comes with

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

    comes with

    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
    IN
    0.47
     insc
    0.45
    кто
    0.44
     skele
    0.42
    </sup>
    0.42
    йно
    0.42
     उपस्थिति
    0.41
    REND
    0.40
    VISIBLE
    0.40
    Halloween
    0.40
    POSITIVE LOGITS
     warnings
    0.55
     फ्रॉम
    0.54
     ۸
    0.50
     with
    0.50
     warranties
    0.49
    s
    0.47
     من
    0.47
    es
    0.46
     आश्वासन
    0.46
     kosten
    0.46
    Activations Density 0.077%

    No Known Activations