© 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. 112578
    Prev
    Next
    INDEX
    Explanations

    prediction of future states

    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
     Sometimes
    -1.29
     durch
    -1.29
     before
    -1.27
    jątk
    -1.25
     start
    -1.25
     Really
    -1.25
     so
    -1.18
     ذلك
    -1.17
     लिए
    -1.15
     beginnings
    -1.14
    POSITIVE LOGITS
     både
    1.53
     réponses
    1.28
    玉ねぎ
    1.27
    both
    1.27
    many
    1.26
     GUARANTEE
    1.22
     arrondissement
    1.20
     soutě
    1.20
    BOTH
    1.19
     хви
    1.19
    Activations Density 0.057%

    No Known Activations