© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43054
    Prev
    Next
    INDEX
    Explanations

    paradoxes and paradoxical ideas

    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
    橦
    -2.48
    詎
    -2.25
    borsa
    -2.23
    偸
    -2.17
    聼
    -2.14
    慊
    -2.14
     xadrez
    -2.14
     feltro
    -2.13
    蟜
    -2.09
    ⎚
    -2.09
    POSITIVE LOGITS
    \
    2.67
    s
    2.56
     {
    2.56
    ti
    2.44
    讽
    2.33
    ID
    2.27
    e
    2.25
    Y
    2.23
    L
    2.23
    </td>
    2.22
    Activations Density 0.003%

    No Known Activations