© 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. 16397
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences

    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
    ivano
    -1.05
     maternidade
    -1.00
     mulher
    -0.98
     udě
    -0.96
    <bos>
    -0.95
    ⽐
    -0.94
     необходи
    -0.93
     vacacionales
    -0.93
     zarządz
    -0.91
     "
    -0.91
    POSITIVE LOGITS
    isław
    1.01
    >',
    1.00
    ,
    1.00
     موض
    0.99
    一の
    0.98
     restTemplate
    0.94
    TestingModule
    0.93
    __('
    0.93
     BaseActivity
    0.93
    ssssssss
    0.93
    Activations Density 0.003%

    No Known Activations