© 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. 32955
    Prev
    Next
    INDEX
    Explanations

    swift type casting or optional access

    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
    lē
    -0.77
     until
    -0.76
    ???:
    -0.75
    ằ
    -0.74
    ARY
    -0.74
    してもら
    -0.73
    UNE
    -0.70
     initialization
    -0.69
    ək
    -0.69
    ??????
    -0.69
    POSITIVE LOGITS
    ?
    1.00
    !
    
    0.89
     aujourd
    0.88
    !
    0.86
    Toluene
    0.85
    jardins
    0.84
     deuxième
    0.81
     отли
    0.77
     jordan
    0.77
     ausein
    0.77
    Activations Density 0.005%

    No Known Activations