© 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-262K
    7. 27491
    Prev
    Next
    INDEX
    Explanations

    power of concepts

    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
    oxicity
    0.50
    是否
    0.43
    Issues
    0.42
    waża
    0.41
     enjeux
    0.40
     типов
    0.40
    रिस
    0.40
    陼
    0.39
     Issues
    0.38
     hostilities
    0.38
    POSITIVE LOGITS
     imagination
    0.70
     hindsight
    0.69
     poderosa
    0.60
     poderos
    0.59
     suggestion
    0.58
     powerful
    0.57
     placebo
    0.56
     poder
    0.55
     puissant
    0.55
     incumb
    0.53
    Activations Density 0.006%

    No Known Activations