© 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. 83706
    Prev
    Next
    INDEX
    Explanations

    full body massage

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

    critical, crucial, explore, consequences

    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
    朱
    0.49
    }\,\
    0.45
    бина
    0.45
    }(\
    0.45
    (\
    0.45
    Snippet
    0.45
    льбе
    0.44
    ParentElement
    0.44
    }<
    0.44
    GreaterThan
    0.44
    POSITIVE LOGITS
     are
    0.50
    鉚
    0.48
     accommodations
    0.48
     mismanagement
    0.48
     عین
    0.47
     wages
    0.46
     हजारों
    0.46
     accommodates
    0.46
    夙
    0.45
    이어
    0.45
    Activations Density 0.001%

    No Known Activations