© 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. 10-GEMMASCOPE-RES-131K
    7. 113857
    Prev
    Next
    INDEX
    Explanations

    words following "and"

    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_10/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
     with
    -2.14
     latter
    -1.88
    ↵
    -1.76
    .
    -1.55
    цыі
    -1.40
     ältere
    -1.37
     both
    -1.35
     one
    -1.34
    –¿
    -1.31
    ↵↵↵
    -1.30
    POSITIVE LOGITS
     Giochi
    1.43
     "'
    1.43
     nhé
    1.39
    e
    1.38
     reflexionar
    1.38
    veloppement
    1.36
    になるので
    1.36
     são
    1.36
    횃
    1.34
     //$
    1.31
    Activations Density 0.136%

    No Known Activations