© 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. 65766
    Prev
    Next
    INDEX
    Explanations

    crime and security

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on uncommon, multi-syllabic technical or specialized nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     vaše
    -1.42
     mať
    -1.16
     establecidas
    -1.12
     refuer
    -1.09
    robat
    -1.05
     legales
    -1.05
    зыв
    -1.04
     wciąż
    -1.04
     inapropiados
    -1.03
     tomaron
    -1.02
    POSITIVE LOGITS
     vetro
    1.13
    \<
    1.08
    nly
    1.07
    用
    1.04
     hiver
    1.01
     $_{\
    1.01
     hlm
    0.98
     تضيف
    0.98
    isierung
    0.96
    🤝
    0.96
    Activations Density 0.099%

    No Known Activations