© 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. 115358
    Prev
    Next
    INDEX
    Explanations

    account or product descriptions

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

    elements

    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
     semblables
    0.41
    诸
    0.41
     parcour
    0.41
    が多い
    0.40
     paired
    0.40
    imposed
    0.39
     menggambarkan
    0.39
    :
    0.39
     skol
    0.38
     variés
    0.38
    POSITIVE LOGITS
     ።
    0.52
    ី
    0.51
    삭
    0.50
     LUMP
    0.48
    cliffe
    0.47
     километ
    0.47
     국제
    0.46
     Calcula
    0.46
     it
    0.46
    ীরে
    0.46
    Activations Density 0.000%

    No Known Activations