© 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. 216923
    Prev
    Next
    INDEX
    Explanations

    building blocks

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

    most crucial

    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
     Ceren
    0.46
     Qar
    0.45
     nerf
    0.45
     kuning
    0.45
     Kro
    0.43
     trội
    0.43
    ^{\
    0.42
    ʳ
    0.42
    aliy
    0.42
     Kanton
    0.42
    POSITIVE LOGITS
    <0x93>
    0.51
    দ
    0.50
    readable
    0.49
    ကြား
    0.49
    ﺩ
    0.48
    ด
    0.48
    ໂ
    0.48
     JANUARY
    0.46
    ប់
    0.46
    ной
    0.45
    Activations Density 0.000%

    No Known Activations