© 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. 157264
    Prev
    Next
    INDEX
    Explanations

    resort, county, intimate, length

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

    embrace your quirks

    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
     아무
    0.55
     అను
    0.43
    </b>
    0.43
     뭐
    0.43
     أل
    0.43
     पूरी
    0.42
    legi
    0.42
     יו
    0.42
    üst
    0.41
    ↵↵
    0.41
    POSITIVE LOGITS
     Counties
    0.56
    نیم
    0.52
     pulsing
    0.50
     охла
    0.50
    a
    0.50
    symbols
    0.50
    த்துள்
    0.48
    数は
    0.47
    county
    0.46
     Coat
    0.46
    Activations Density 0.001%

    No Known Activations