© 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. 112120
    Prev
    Next
    INDEX
    Explanations

    license includes

    np_acts-logits-general · gemini-2.5-flash-lite

    parenthetical remarks or metadata in technical and formal documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    もありました
    -1.59
    -
    -1.52
     puntuación
    -1.38
    がありました
    -1.38
     here
    -1.38
     only
    -1.38
     actualización
    -1.38
    その時
    -1.35
     porción
    -1.34
     misschien
    -1.34
    POSITIVE LOGITS
    including
    1.87
     APPEALS
    1.59
    媖
    1.55
    بوابة
    1.48
     including
    1.43
     idee
    1.41
    ｓ
    1.40
    ｔ
    1.39
    Здра
    1.38
     ͡°
    1.37
    Activations Density 0.005%

    No Known Activations