© 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. 10-GEMMASCOPE-RES-131K
    7. 114038
    Prev
    Next
    INDEX
    Explanations

    as we saw

    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
    Negative Logits
    </i>
    -1.63
     おり
    -1.41
    ধ
    -1.26
    }},\
    -1.25
    er
    -1.19
    agissait
    -1.19
     Because
    -1.18
    bindParam
    -1.13
    henswürdigkeiten
    -1.13
     both
    -1.12
    POSITIVE LOGITS
     it
    1.99
    prek
    1.45
     otra
    1.44
    ーーー
    1.41
     there
    1.40
    媗
    1.40
    ーーーー
    1.38
     WaitForSeconds
    1.38
    我才
    1.36
     rápidamente
    1.34
    Activations Density 0.024%

    No Known Activations