© 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. 76560
    Prev
    Next
    INDEX
    Explanations

    as if it were

    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
     PLWABN
    -0.84
    CDK
    -0.79
    ]=(
    -0.76
    更是
    -0.75
     may
    -0.74
    viste
    -0.73
     will
    -0.73
     encantan
    -0.71
     pretty
    -0.71
    롭
    -0.71
    POSITIVE LOGITS
     were
    2.31
     fosse
    1.57
     fossero
    1.25
     gdyby
    1.21
     WERE
    1.05
     fuera
    1.03
     weren
    1.00
     avesse
    0.99
    Were
    0.98
    were
    0.96
    Activations Density 0.025%

    No Known Activations