© 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. 34-GEMMASCOPE-RES-131K
    7. 93519
    Prev
    Next
    INDEX
    Explanations

    support group

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

    The neuron fires on mentions of support or support‐group contexts (e.g., “support group,” “joining a support group,” “peer support”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    oczes
    -0.87
     scolaires
    -0.83
    ipedia
    -0.82
    azzi
    -0.80
    
    -0.80
     poverty
    -0.79
    legging
    -0.79
     kombiniert
    -0.78
     situés
    -0.77
     Meldung
    -0.77
    POSITIVE LOGITS
     group
    3.20
     groups
    2.92
    group
    2.39
    groups
    2.31
     Groups
    2.22
     grupo
    2.17
     Group
    2.11
    Groups
    2.11
     grupos
    2.09
     گروه
    2.03
    Activations Density 0.040%

    No Known Activations