© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 23934
    Prev
    Next
    INDEX
    Explanations

    axis of rotation, perpendicular to

    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
     unſ
    -2.11
    ’
    -2.03
    踯
    -1.96
     広場
    -1.82
    .
    -1.80
    ₶
    -1.80
     باسلام
    -1.79
     одном
    -1.76
    饹
    -1.74
    couvrir
    -1.71
    POSITIVE LOGITS
     händ
    2.08
    蛧
    1.87
    OOTDTY
    1.81
     konkre
    1.73
     $
    1.72
    是非常
    1.70
    我和
    1.70
     axis
    1.69
    你和
    1.69
     burgeoning
    1.66
    Activations Density 0.018%

    No Known Activations