© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32097
    Prev
    Next
    INDEX
    Explanations

    errors and invalid states

    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
     disappointments
    -0.96
     undisturbed
    -0.89
     Anno
    -0.89
    ÇÃO
    -0.88
     controversi
    -0.86
    альные
    -0.86
     mediocrity
    -0.86
     FAILED
    -0.85
    sssss
    -0.85
    дные
    -0.84
    POSITIVE LOGITS
     wrong
    2.95
     too
    2.59
     invalid
    2.58
     incorrect
    2.30
     insufficient
    2.06
     no
    2.00
     слишком
    1.98
     bad
    1.95
    Wrong
    1.91
     missing
    1.91
    Activations Density 0.053%

    No Known Activations