© 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. 23247
    Prev
    Next
    INDEX
    Explanations

    pow, powder, Powell

    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
     Voss
    0.42
    Ⲗ
    0.41
    فته
    0.41
     parametros
    0.38
    ギリス
    0.37
     filings
    0.37
    ULO
    0.36
     writs
    0.36
     CSC
    0.35
    分布
    0.35
    POSITIVE LOGITS
    Pow
    0.72
     Powder
    0.61
     powders
    0.61
     powder
    0.61
    粉
    0.56
     Pow
    0.55
     powdery
    0.55
     粉
    0.55
    pow
    0.52
    powder
    0.48
    Activations Density 0.007%

    No Known Activations