© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 109297
    Prev
    Next
    INDEX
    Explanations

    breath, teeth, heart

    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_262k_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
     SCI
    0.45
     Strad
    0.43
     Glaub
    0.42
    凸
    0.41
     QD
    0.40
     Pelham
    0.39
     DOL
    0.38
    詷
    0.38
     Goh
    0.37
     treated
    0.37
    POSITIVE LOGITS
    orama
    0.39
     affiliates
    0.39
     personalise
    0.38
     organisations
    0.37
     flavours
    0.37
    imeric
    0.37
     frameworks
    0.36
     recognises
    0.36
     outcomes
    0.35
     presentation
    0.35
    Activations Density 0.003%

    No Known Activations