© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 242665
    Prev
    Next
    INDEX
    Explanations

    listed and located

    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
     montón
    0.51
     📫
    0.51
     múltipl
    0.50
     múltiples
    0.50
     自動
    0.49
     സ്വാതന്ത്ര
    0.48
     simonsen
    0.47
     Drinfeld
    0.47
     reforzar
    0.47
     independente
    0.47
    POSITIVE LOGITS
    质
    0.55
     Ladd
    0.46
    了这个
    0.45
    时
    0.45
    问题
    0.44
     Trou
    0.43
     Has
    0.43
     Quality
    0.43
    '][
    0.42
    一样
    0.42
    Activations Density 0.008%

    No Known Activations