© 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. 20626
    Prev
    Next
    INDEX
    Explanations

    up then

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

    questions asking "what" or asking to "find"

    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
     х
    0.42
     hereto
    0.42
     ਟ
    0.42
     водо
    0.42
    EventHandler
    0.40
    ')),
    0.40
    ')).
    0.39
    :'.
    0.39
     巻
    0.38
    鉄
    0.37
    POSITIVE LOGITS
    impi
    0.41
    essi
    0.41
    arnya
    0.38
    ingu
    0.38
    irma
    0.38
    ami
    0.37
    ermi
    0.37
    ysi
    0.37
     generalizing
    0.37
     ഇത്
    0.37
    Activations Density 0.000%

    No Known Activations