© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 64446
    Prev
    Next
    INDEX
    Explanations

    Markdown/HTML structural markers

    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
    
    -1.47
     said
    -0.88
     also
    -0.87
    }}=\
    -0.84
    enské
    -0.83
    ndig
    -0.82
     artysty
    -0.81
     can
    -0.81
    anshu
    -0.81
    )。
    -0.76
    POSITIVE LOGITS
    <h3>
    3.72
    ###
    1.40
    ,”
    1.27
    ,"
    1.25
     ###
    1.24
    ),"
    1.23
    "},
    1.21
    '],
    1.15
    ,’
    1.12
    ;</
    1.09
    Activations Density 0.012%

    No Known Activations