© 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. 34418
    Prev
    Next
    INDEX
    Explanations

    super algebras

    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
     唯美
    -1.18
    Ꮀ
    -1.18
     kvalit
    -1.17
     internetu
    -1.16
     插图
    -1.16
     incrí
    -1.15
     Vainqueur
    -1.15
     esmeralda
    -1.14
     菇
    -1.13
    焢
    -1.09
    POSITIVE LOGITS
    ac
    1.35
    ar
    1.34
    f
    1.30
    p
    1.30
    an
    1.28
    j
    1.26
    g
    1.24
    L
    1.23
    en
    1.21
     A
    1.21
    Activations Density 0.079%

    No Known Activations