© 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. 130154
    Prev
    Next
    INDEX
    Explanations

    make, provide, protect, help, spread

    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
     لأنه
    -1.14
     Anbieter
    -1.09
    prende
    -1.07
     nowych
    -1.05
     bricolaje
    -1.05
    uberge
    -1.04
    arım
    -1.03
     chyb
    -1.03
     tradicionais
    -1.01
    совет
    -1.00
    POSITIVE LOGITS
     this
    1.40
     help
    1.22
    はこの
    1.13
    の
    1.09
     protect
    1.05
     questo
    1.02
     questa
    1.02
     dieser
    1.00
     此
    0.98
    ａ
    0.98
    Activations Density 0.034%

    No Known Activations