© 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. 247538
    Prev
    Next
    INDEX
    Explanations

    beginning phrases of sentences

    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
    چے
    0.45
    윤
    0.45
    norms
    0.45
     Chag
    0.45
    섯
    0.44
     crowns
    0.44
    tanh
    0.44
     Wied
    0.44
    धव
    0.44
     இருந்தார்
    0.44
    POSITIVE LOGITS
    ika
    0.47
    土地
    0.46
    ickou
    0.44
    onti
    0.44
     થ
    0.43
    4
    0.43
    offel
    0.42
     шуда
    0.42
    ViewController
    0.41
    Advertisement
    0.41
    Activations Density 0.001%

    No Known Activations