© 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. 76732
    Prev
    Next
    INDEX
    Explanations

    lisk, standard, introduction, white

    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
     سينما
    -0.76
    ceded
    -0.73
    社會
    -0.70
     почти
    -0.68
    Feed
    -0.68
     傳
    -0.67
    ьогодні
    -0.66
    Almost
    -0.66
     hampir
    -0.66
     crítica
    -0.66
    POSITIVE LOGITS
     NEO
    0.90
    NEP
    0.77
     consensus
    0.77
    trong
    0.77
    korb
    0.76
     ABI
    0.75
     Tx
    0.75
     Stor
    0.75
     GAS
    0.74
    izate
    0.74
    Activations Density 0.018%

    No Known Activations