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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26583
    Prev
    Next
    INDEX
    Explanations

    XML, JSON, Java types

    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
     by
    -1.65
    があって
    -1.26
    などが
    -1.21
     in
    -1.13
    璟
    -1.11
     Quy
    -1.08
    があります
    -1.05
    もあり
    -1.01
    pyr
    -1.01
    淼
    -1.00
    POSITIVE LOGITS
     (!__
    1.30
    割と
    1.20
     erwäh
    1.20
    espé
    1.16
    昨日は
    1.14
    昨日の
    1.13
    مقاله
    1.12
     recaud
    1.12
     Recently
    1.09
    Those
    1.09
    Activations Density 0.027%

    No Known Activations