© 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. 14213
    Prev
    Next
    INDEX
    Explanations

    Q:, V:, Friday, It, rewritten

    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
     only
    -1.47
     at
    -1.31
    Only
    -1.21
     an
    -1.18
     Some
    -1.16
     Only
    -1.15
    Forty
    -1.14
     all
    -1.13
     ONLY
    -1.12
     Four
    -1.09
    POSITIVE LOGITS
    ᨆ
    1.34
    Rys
    1.28
    และ
    1.23
     lavanda
    1.22
    などの
    1.22
    などに
    1.21
     другим
    1.19
     fotografii
    1.19
     rapporter
    1.16
     politie
    1.16
    Activations Density 0.002%

    No Known Activations