© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55812
    Prev
    Next
    INDEX
    Explanations

    group and groupName

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     particularly
    -0.85
     userName
    -0.78
    Stret
    -0.77
    ┻
    -0.76
     specific
    -0.75
     valuable
    -0.75
     especially
    -0.74
     Bedeutung
    -0.74
     Aunt
    -0.73
    Aunt
    -0.72
    POSITIVE LOGITS
     subgroups
    1.34
     subgroup
    1.23
    GroupName
    1.20
    groupName
    1.14
    group
    1.13
     Group
    1.10
    ListGroup
    1.06
    Group
    1.02
     groupes
    0.97
     Gruppen
    0.93
    Activations Density 0.063%

    No Known Activations