© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90467
    Prev
    Next
    INDEX
    Explanations

    shapes and points

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

    The neuron detects descriptive terms referring to shape or form (e.g. “rounded,” “pointed,” “arched,” “obtuse,” “pupiform,” etc.).

    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
    romeda
    -1.41
    uating
    -1.39
    quing
    -1.38
     grasas
    -1.36
    
    -1.34
     employé
    -1.31
     creativos
    -1.30
    WARDS
    -1.28
     vektör
    -1.28
    ној
    -1.27
    POSITIVE LOGITS
    6
    1.31
     It
    1.16
    _
    1.15
     of
    1.13
    3
    1.13
     We
    1.13
     each
    1.13
     .
    1.08
     at
    1.07
    <b>
    1.05
    Activations Density 0.098%

    No Known Activations