© 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. 34-GEMMASCOPE-RES-131K
    4. 50458
    Prev
    Next
    INDEX
    Explanations

    register names ending in CLR

    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
    Obtener
    -0.90
     Naciones
    -0.82
     would
    -0.79
    ^+
    -0.78
    IALES
    -0.77
    MANUAL
    -0.75
     选
    -0.74
     algod
    -0.73
     Zufall
    -0.73
    gemaakt
    -0.73
    POSITIVE LOGITS
    reg
    1.00
    Reg
    0.99
     REG
    0.98
     Reg
    0.98
     reg
    0.95
    REG
    0.90
     register
    0.79
    ereg
    0.79
    inheritDoc
    0.76
     regist
    0.75
    Activations Density 0.000%

    No Known Activations