© 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. 128886
    Prev
    Next
    INDEX
    Explanations

    What is

    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
     behand
    -1.16
     ESTADO
    -1.13
     their
    -1.13
     his
    -1.09
     COOKIES
    -1.05
     contacter
    -1.05
    𝐉
    -1.05
     hafta
    -1.03
     onDestroy
    -1.02
     RECOMEND
    -1.02
    POSITIVE LOGITS
     how
    1.34
    怎樣
    1.23
    𓏸
    1.10
     infallible
    1.09
     penyanyi
    1.04
     ähnlichen
    1.01
    al
    0.96
    ͌
    0.96
    ῇ
    0.96
    ̓
    0.94
    Activations Density 0.035%

    No Known Activations