© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67152
    Prev
    Next
    INDEX
    Explanations

    years and quarterly

    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
     without
    -1.41
     from
    -1.37
     at
    -1.28
     if
    -1.28
     when
    -1.27
     especias
    -1.26
     but
    -1.24
     or
    -1.20
     on
    -1.20
     before
    -1.19
    POSITIVE LOGITS
     conster
    1.12
     triom
    1.10
     perpé
    1.06
    づくり
    1.04
     goddamn
    1.03
    聚集
    1.02
    nischer
    1.01
     FEBR
    1.01
     GRATU
    1.00
    かも知
    1.00
    Activations Density 0.069%

    No Known Activations