© 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. 71500
    Prev
    Next
    INDEX
    Explanations

    australian place names

    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
    獁
    -2.78
    стреча
    -2.61
    狁
    -2.58
    gantung
    -2.50
    Also
    -2.39
     він
    -2.39
     ");
    -2.38
     mereka
    -2.34
    ftrag
    -2.31
    鴣
    -2.27
    POSITIVE LOGITS
    au
    4.38
    いえば
    2.75
    *
    2.70
    ay
    2.63
    {
    2.59
    ised
    2.59
    u
    2.55
    j
    2.55
     they
    2.53
    ii
    2.41
    Activations Density 0.003%

    No Known Activations