© 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. 181431
    Prev
    Next
    INDEX
    Explanations

    recent years

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

    specific technical terms and options

    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
     juez
    0.52
     jueces
    0.46
    ्यूर
    0.46
     iaa
    0.46
    恿
    0.45
     probs
    0.45
     मिलेगी
    0.45
    enet
    0.45
    éléments
    0.45
     anillos
    0.44
    POSITIVE LOGITS
     ખા
    0.45
    冷蔵
    0.45
     hernia
    0.44
    ulty
    0.43
     categorized
    0.43
     Fairmont
    0.41
    喰
    0.41
     categor
    0.41
     Stain
    0.40
     legitimately
    0.40
    Activations Density 0.001%

    No Known Activations