© 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. 57773
    Prev
    Next
    INDEX
    Explanations

    cities after "in"

    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
    を
    -1.76
    などを
    -1.73
    では
    -1.43
    <bos>
    -1.35
    などの
    -1.35
    や
    -1.34
    で
    -1.32
    味が
    -1.30
    なども
    -1.30
     магазине
    -1.30
    POSITIVE LOGITS
     downtown
    1.77
     accordance
    1.60
     which
    1.45
     Germany
    1.41
     Italy
    1.39
     that
    1.38
     the
    1.35
     their
    1.32
     what
    1.31
     Spain
    1.29
    Activations Density 0.125%

    No Known Activations