© 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. 55660
    Prev
    Next
    INDEX
    Explanations

    connectors and determiners

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

    Starts with "And" followed by common phrases

    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
    蓄
    0.46
     highly
    0.44
    ELECT
    0.43
    ポリシー
    0.43
    ㎛
    0.42
    步骤
    0.41
     TeV
    0.41
    粗
    0.41
     prior
    0.40
    ##
    0.40
    POSITIVE LOGITS
     And
    0.48
     Corinthians
    0.46
     Revelation
    0.44
    ແລະ
    0.43
     ແລະ
    0.43
    ર્ક
    0.42
     mellett
    0.42
     nombr
    0.41
    And
    0.41
    jak
    0.40
    Activations Density 0.011%

    No Known Activations