© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55918
    Prev
    Next
    INDEX
    Explanations

    file extensions and compression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saltwater
    0.43
    舏
    0.42
    果
    0.41
     mime
    0.40
    щей
    0.40
     untitled
    0.39
     YAML
    0.39
    Dockerfile
    0.38
    webp
    0.38
    Stylesheet
    0.38
    POSITIVE LOGITS
     décisions
    0.43
     prestation
    0.42
     Gerhard
    0.40
     '_
    0.39
    ্সি
    0.39
     Eltern
    0.39
     Espagne
    0.38
     decisão
    0.38
     नेहरू
    0.38
     Coating
    0.38
    Activations Density 0.022%

    No Known Activations