© 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. 2249
    Prev
    Next
    INDEX
    Explanations

    items or categories

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

    defining elements or starting points

    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
     Lanc
    0.41
     Belo
    0.39
     Ingl
    0.38
     bulld
    0.38
    éticos
    0.38
    ඪ
    0.37
    靕
    0.37
     Faun
    0.37
    ících
    0.36
    riven
    0.36
    POSITIVE LOGITS
     대신
    0.49
    。
    0.49
    代わりに
    0.48
     followed
    0.44
    followed
    0.44
    whereas
    0.41
     whereas
    0.41
    instead
    0.40
    ；
    0.40
     brunt
    0.39
    Activations Density 0.252%

    No Known Activations