© 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. 7524
    Prev
    Next
    INDEX
    Explanations

    Alexander, Oleksandr, Alexandros

    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
    '
    -5.50
     
    -2.80
    ？！”
    -2.59
     is
    -2.33
     "
    -2.33
     The
    -2.27
    了他的
    -2.25
    </strong>
    -2.14
     '
    -2.13
    &
    -2.09
    POSITIVE LOGITS
    蛩
    3.03
    羕
    2.89
    »،
    2.59
    鸮
    2.42
    鐒
    2.41
    Ꮵ
    2.41
     Hinsicht
    2.39
    ፱
    2.38
     sizzling
    2.36
    媜
    2.36
    Activations Density 0.010%

    No Known Activations