© 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. 93079
    Prev
    Next
    INDEX
    Explanations

    type definitions

    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
    soever
    -1.06
     ältere
    -1.05
     übri
    -1.03
    n
    -1.03
     rhein
    -0.96
     după
    -0.92
    s
    -0.91
     He
    -0.90
     appoints
    -0.90
     titled
    -0.88
    POSITIVE LOGITS
     getType
    1.45
    getType
    1.21
     TYPE
    1.16
     typy
    1.14
     Type
    1.12
     DbType
    1.08
     starost
    1.06
     setType
    1.05
     SqlDbType
    1.05
     typeName
    1.05
    Activations Density 0.124%

    No Known Activations