© 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. 68293
    Prev
    Next
    INDEX
    Explanations

    handles events and objects

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

    This neuron fires on tokens containing the substring “handle” (e.g. handles, unhandled).

    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
    }
    -2.56
    -2.36
    1
    -2.25
     две
    -2.11
    2
    -2.02
    6
    -1.98
    9
    -1.97
    自己的
    -1.96
    两
    -1.94
     inception
    -1.88
    POSITIVE LOGITS
    </h2>
    2.64
    handles
    2.30
     handles
    2.20
    𓆜
    2.00
     then
    2.00
     diversa
    1.95
    ဴ
    1.93
     also
    1.91
     probably
    1.91
     to
    1.89
    Activations Density 0.002%
    No Known Activations