© 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. 186044
    Prev
    Next
    INDEX
    Explanations

    to me

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

    lower memory usage

    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
    幫
    0.51
     ajutor
    0.46
     コン
    0.45
     filoz
    0.44
     الزد
    0.43
    ਿਰ
    0.43
     ঐতি
    0.43
     filozof
    0.43
     expeditions
    0.43
     sposob
    0.42
    POSITIVE LOGITS
     Holly
    0.45
    榉
    0.44
     Kline
    0.44
    ),\\
    0.43
    Holly
    0.42
    itemize
    0.42
    abelian
    0.41
     unterschiedlich
    0.41
    flatten
    0.41
    ۸
    0.41
    Activations Density 0.001%

    No Known Activations