© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 17943
    Prev
    Next
    INDEX
    Explanations

    Prefixes of names and compound words

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

    Hemlock

    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
     icono
    0.49
     deuter
    0.44
     youll
    0.42
     aprox
    0.42
     kaleidoscope
    0.41
     această
    0.41
     deinen
    0.41
    ʌ
    0.41
    ®.
    0.41
     tämä
    0.41
    POSITIVE LOGITS
    man
    0.50
     Levine
    0.49
     himself
    0.48
    iman
    0.47
    owski
    0.47
     McGowan
    0.47
     Olson
    0.46
     Pereira
    0.45
     Anthony
    0.45
     Garcia
    0.45
    Activations Density 0.026%

    No Known Activations