© 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. 39272
    Prev
    Next
    INDEX
    Explanations

    word followed by connector

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

    asking questions

    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
    bergs
    0.45
    वाड़ा
    0.43
    向前
    0.43
    एनजी
    0.43
    letts
    0.42
    涌
    0.42
    及时
    0.42
    k
    0.42
    افظ
    0.41
    翘
    0.41
    POSITIVE LOGITS
     روغن
    0.52
     Bacter
    0.47
     ライ
    0.47
     CheckKey
    0.46
    Regulation
    0.46
     ကျွန်
    0.46
     キー
    0.46
     ám
    0.46
     売
    0.45
     실험
    0.45
    Activations Density 0.001%

    No Known Activations