© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64644
    Prev
    Next
    INDEX
    Explanations

    Apple followed by related terms

    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_22/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
    ’
    -3.58
    '
    -2.81
     ‘
    -2.55
    ”
    -2.55
    ar
    -2.52
    on
    -2.44
     
    -2.41
    at
    -2.33
    o
    -2.28
     is
    -2.23
    POSITIVE LOGITS
    鰱
    2.78
    értel
    2.64
    𓄹
    2.61
    pulsera
    2.55
    Ꮨ
    2.50
    鐒
    2.50
    förm
    2.47
    Počet
    2.39
    鲽
    2.36
    𓍊
    2.36
    Activations Density 0.010%

    No Known Activations