© 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. 222326
    Prev
    Next
    INDEX
    Explanations

    reverse, next, administrative, typically, minutes, you

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

    manipulating sound waves

    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
     aanv
    0.50
     dijete
    0.49
    ק
    0.48
     posle
    0.47
    ین
    0.47
    უხ
    0.46
     semaines
    0.45
     direkte
    0.44
     eerst
    0.43
     veya
    0.43
    POSITIVE LOGITS
    。
    0.56
    VOC
    0.46
    blocks
    0.46
    lang
    0.44
    getBlock
    0.42
     Repert
    0.41
    itons
    0.41
     ভূত
    0.41
    咕
    0.41
    fab
    0.40
    Activations Density 0.001%

    No Known Activations