© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117486
    Prev
    Next
    INDEX
    Explanations

    that clause introducers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.53
    וּ
    -1.47
     deswegen
    -1.39
    וֹ
    -1.26
     वो
    -1.23
    ַּ
    -1.20
    pantalón
    -1.18
    𐌸
    -1.16
     básicamente
    -1.13
    っぷり
    -1.11
    POSITIVE LOGITS
     it
    2.14
     there
    1.95
     in
    1.70
     nothing
    1.52
     such
    1.39
     from
    1.36
     when
    1.34
     by
    1.33
     no
    1.30
     if
    1.30
    Activations Density 0.020%

    No Known Activations