© 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. 32612
    Prev
    Next
    INDEX
    Explanations

    term of use, term for

    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
    Negative Logits
     We
    -3.39
     использования
    -2.52
     ruines
    -2.47
    とその
    -2.44
    точници
    -2.27
     jardins
    -2.14
     drenaje
    -2.13
     geladeira
    -2.09
     thwarted
    -2.09
    という意味
    -2.09
    POSITIVE LOGITS
    S
    3.36
    ra
    3.36
    re
    3.16
    珢
    3.00
    1
    2.78
    ta
    2.75
    er
    2.64
    ar
    2.59
    h
    2.55
    il
    2.53
    Activations Density 0.040%

    No Known Activations