© 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. 15680
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

    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
     Whilst
    -1.53
     whilst
    -1.48
    Whilst
    -1.45
     Amongst
    -1.21
     amongst
    -1.19
     данного
    -1.08
     zukünf
    -1.02
    casted
    -1.00
    chinese
    -0.98
    このような
    -0.97
    POSITIVE LOGITS
     sejumlah
    1.16
     треба
    1.14
     its
    1.13
     staffers
    1.10
    ]=(
    1.07
    🔟
    1.02
     cominci
    1.00
    достатки
    0.98
    赢得
    0.98
     пять
    0.98
    Activations Density 0.062%

    No Known Activations