© 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. 64720
    Prev
    Next
    INDEX
    Explanations

    detecting collisions, routes, methods

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

    This neuron activates on occurrences of the root “detect,” i.e. words like “detect,” “detection,” or “detected.”

    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
    g
    -2.44
     predominant
    -2.19
                
    -2.16
    ↵↵
    -2.16
     inept
    -2.13
    da
    -2.06
     comparatively
    -2.06
    subsection
    -2.06
     gefährlich
    -2.02
     zuge
    -1.98
    POSITIVE LOGITS
    部分は
    2.50
     become
    2.44
     you
    2.38
     pessoais
    2.30
    zelfde
    2.27
     encontram
    2.22
     permitem
    2.22
    生活的
    2.20
    部分が
    2.14
    箆
    2.11
    Activations Density 0.032%

    No Known Activations