© 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. 10-GEMMASCOPE-RES-131K
    7. 44376
    Prev
    Next
    INDEX
    Explanations

    Richmond place names

    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_10/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
    .”
    -3.16
     получил
    -3.08
    if
    -3.02
    u
    -2.67
    on
    -2.56
     savor
    -2.55
     anche
    -2.44
    有点
    -2.34
     crippling
    -2.33
    with
    -2.25
    POSITIVE LOGITS
    𞤢
    3.92
    酲
    3.36
    聼
    3.25
    䥑
    3.16
    Ꭳ
    3.08
    趼
    3.05
    赑
    3.00
    祧
    2.97
    sandalia
    2.92
    珰
    2.89
    Activations Density 0.002%

    No Known Activations