© 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. 106023
    Prev
    Next
    INDEX
    Explanations

    listing features and components

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

    building large structures

    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
    分别为
    0.47
    ulfillment
    0.44
    {
    0.44
    ཎ
    0.43
    ర్‌
    0.43
    andid
    0.43
    idora
    0.42
    }
    0.42
    PARATOR
    0.42
    bola
    0.41
    POSITIVE LOGITS
     hilltop
    0.47
     ا
    0.45
     पीछ
    0.45
    وصل
    0.45
     Building
    0.45
     building
    0.44
     aonde
    0.44
     dungeons
    0.42
     towering
    0.42
     bustling
    0.42
    Activations Density 0.002%

    No Known Activations