© 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. 47875
    Prev
    Next
    INDEX
    Explanations

    order receipt

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

    water purification chemicals

    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
    us
    0.56
    an
    0.47
    Black
    0.47
    [.
    0.46
    <code>
    0.45
     पिछड़े
    0.45
    文件夹
    0.44
    </code>
    0.43
    atangan
    0.43
    Detail
    0.43
    POSITIVE LOGITS
     hydrological
    0.52
     víz
    0.51
     hydrology
    0.50
     wybor
    0.48
     tendrás
    0.48
    の水
    0.48
     água
    0.47
     tubig
    0.47
     遊
    0.47
     centrifugation
    0.46
    Activations Density 0.000%

    No Known Activations