© 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. 115989
    Prev
    Next
    INDEX
    Explanations

    touch screen displays

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

    prices incentivize

    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
    最具
    0.49
     portanto
    0.48
     πιο
    0.46
     மிகப்
    0.46
     மிகவும்
    0.45
     centimetres
    0.45
    </u>
    0.44
     potenti
    0.44
     අනුව
    0.43
     tumour
    0.43
    POSITIVE LOGITS
    Touch
    0.54
    怿
    0.46
     Touch
    0.46
    Fence
    0.44
     TOUCH
    0.43
    fence
    0.42
    ਏ
    0.42
    touch
    0.42
     prv
    0.42
    Commercial
    0.41
    Activations Density 0.000%

    No Known Activations