© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78027
    Prev
    Next
    INDEX
    Explanations

    ideal, perfect, suitable

    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
     belangrij
    -0.96
    このように
    -0.93
    ceni
    -0.92
    edere
    -0.91
    浓郁
    -0.89
     Jenderal
    -0.88
     ἄ
    -0.88
    seigneur
    -0.85
    ilija
    -0.85
    Föld
    -0.85
    POSITIVE LOGITS
     suitable
    5.06
     ideal
    4.75
     perfect
    4.53
    suitable
    3.58
    ideal
    3.53
     suited
    3.48
     Suitable
    3.47
    适合
    3.34
     مناسب
    3.30
    Suitable
    3.28
    Activations Density 0.212%

    No Known Activations