© 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. 8516
    Prev
    Next
    INDEX
    Explanations

    under control or get straight

    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
    -
    -2.17
    --
    -2.14
    $
    -2.03
     этих
    -1.91
     "
    -1.80
    --"
    -1.74
    -"
    -1.73
    窦
    -1.50
     same
    -1.49
     verhindert
    -1.48
    POSITIVE LOGITS
    ändigen
    2.13
    ㆁ
    1.67
     drau
    1.51
     Había
    1.51
    ⇰
    1.48
     tlie
    1.48
     Mientras
    1.43
     poil
    1.42
    готовки
    1.41
    große
    1.40
    Activations Density 0.012%

    No Known Activations