© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 555
    Prev
    Next
    INDEX
    Explanations

    rest assured

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

    words ending in -est or -ist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zem
    0.44
    ised
    0.41
    ště
    0.40
     दोषी
    0.39
    chten
    0.39
     Hager
    0.38
    atorics
    0.38
    卑
    0.38
    eret
    0.37
    zza
    0.37
    POSITIVE LOGITS
    aurant
    1.04
    ruction
    0.97
    ricted
    0.95
    ructions
    0.93
    ்ட
    0.92
    ructure
    0.91
    aurants
    0.89
    ruct
    0.86
    ricting
    0.85
    rict
    0.84
    Activations Density 0.557%

    No Known Activations