© 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. 31549
    Prev
    Next
    INDEX
    Explanations

    words starting with "Under"

    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
     Если
    -1.09
    Still
    -1.05
    Even
    -1.03
    Now
    -1.02
    Should
    -1.02
    What
    -1.00
    Looking
    -0.99
     If
    -0.98
    Then
    -0.97
    饪
    -0.95
    POSITIVE LOGITS
    neath
    1.14
    嗖
    1.10
    writers
    1.08
    濵
    1.08
    ኾ
    1.06
    尨
    1.05
     pracuje
    1.03
     incompar
    1.02
    ckets
    1.02
    IEU
    1.01
    Activations Density 0.031%

    No Known Activations