© 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. 216543
    Prev
    Next
    INDEX
    Explanations

    attention on

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

    technical operations and connections

    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
    फत
    0.46
     routinely
    0.46
    ?
    0.45
     obsess
    0.44
    igis
    0.44
     lately
    0.44
    ulte
    0.43
     buys
    0.43
     I
    0.43
    ાલુ
    0.42
    POSITIVE LOGITS
    lict
    0.50
     વિચાર
    0.45
    達成
    0.44
     مک
    0.44
     እየሱስ
    0.44
    ショナル
    0.44
    heritage
    0.44
    歿
    0.43
     行っ
    0.43
    Dictionary
    0.43
    Activations Density 0.000%

    No Known Activations