© 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. 22-GEMMASCOPE-RES-131K
    7. 26550
    Prev
    Next
    INDEX
    Explanations

    patent applications and disclosures

    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_22/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
     trug
    -1.01
     взять
    -0.96
    ՚
    -0.95
     Πε
    -0.93
     ‘
    -0.93
     misst
    -0.93
    lové
    -0.92
     bewilder
    -0.91
    等
    -0.90
     bizarre
    -0.89
    POSITIVE LOGITS
     with
    1.13
    Nonsense
    1.03
     iniciado
    1.03
    ζει
    1.01
    Ито
    1.00
    Ehh
    1.00
    攵
    1.00
    uração
    1.00
     only
    0.99
    Armin
    0.99
    Activations Density 0.004%

    No Known Activations