© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102956
    Prev
    Next
    INDEX
    Explanations

    in or with prepositions

    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
     Anſ
    -1.64
     nadru
    -1.61
    getreten
    -1.57
    ႐
    -1.48
    droje
    -1.48
    reisen
    -1.47
     Reſ
    -1.45
    blume
    -1.41
     poby
    -1.41
    fører
    -1.40
    POSITIVE LOGITS
    Despite
    1.70
    どうなる
    1.60
    Whether
    1.59
     that
    1.59
    Both
    1.55
    Although
    1.55
    Regardless
    1.53
    彼らの
    1.52
     که
    1.50
     что
    1.48
    Activations Density 0.149%

    No Known Activations