© 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. 21084
    Prev
    Next
    INDEX
    Explanations

    will followed by a verb

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

    completing patterns

    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
     prediksi
    0.48
    鈺
    0.46
    的這個
    0.45
     Ape
    0.45
     rado
    0.45
    पीजी
    0.44
    uminescent
    0.44
    იდ
    0.43
    uminescence
    0.43
     SCH
    0.43
    POSITIVE LOGITS
     खासा
    0.50
    UL
    0.45
    Spend
    0.45
    DU
    0.44
    BODY
    0.44
    e
    0.44
    er
    0.43
     Можно
    0.42
     घंटों
    0.42
    Box
    0.42
    Activations Density 0.000%

    No Known Activations