© 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. 10-GEMMASCOPE-RES-131K
    7. 15372
    Prev
    Next
    INDEX
    Explanations

    organization names and technical terms

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

    The neuron fires on tokens that use internal capitalization (TitleCase or CamelCase) such as mixed-case identifiers and proper names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
                    
    -3.23
     treacherous
    -2.53
     genaue
    -2.36
     rispondere
    -2.33
     spezielle
    -2.27
     orchestrated
    -2.25
     eigentliche
    -2.25
     THREE
    -2.23
     citoyens
    -2.20
     \
    -2.19
    POSITIVE LOGITS
    蛧
    2.50
     interesan
    2.42
    傀
    2.28
    玏
    2.28
    ☑
    2.25
    𞤢
    2.25
     encontraban
    2.19
     apie
    2.17
     Also
    2.11
    derdag
    2.11
    Activations Density 0.006%

    No Known Activations