© 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. 15847
    Prev
    Next
    INDEX
    Explanations

    primary election candidates

    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
    ׇ
    -1.25
     étanche
    -1.19
     MwSt
    -1.16
     گیاه
    -1.10
     régle
    -1.10
     mesmas
    -1.09
    CBD
    -1.09
     النبات
    -1.08
    \
    -1.06
    Pranala
    -1.04
    POSITIVE LOGITS
    ִּ
    1.45
    ּוֹ
    1.35
     Wednesday
    1.32
    ֵּ
    1.32
     Tuesday
    1.25
    ְּ
    1.23
     gostaria
    1.16
     ViewHolder
    1.16
    त्म
    1.16
    alny
    1.15
    Activations Density 0.041%

    No Known Activations