© 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. 165060
    Prev
    Next
    INDEX
    Explanations

    my daily, your

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

    achieve, stop, working, system

    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
    ales
    0.46
    ৩
    0.46
    are
    0.44
    三個
    0.44
    ០
    0.44
    뚤
    0.44
     जानकर
    0.43
    //$
    0.43
    医師
    0.43
    的海
    0.43
    POSITIVE LOGITS
    ரஜன்
    0.50
     inseparable
    0.49
     pilgr
    0.49
     veineux
    0.48
     disorientation
    0.44
     forgery
    0.43
    Ᏼ
    0.43
     exhilarating
    0.43
     cesse
    0.43
     pilgrimage
    0.42
    Activations Density 0.001%

    No Known Activations