© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7075
    Prev
    Next
    INDEX
    Explanations

    smallness

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

    small, smaller, smallest

    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
    icur
    0.34
    ArchiveAction
    0.33
    膘
    0.33
    દાવાદ
    0.32
    FilterChain
    0.32
    嗕
    0.32
    ဃ
    0.32
    ണാ
    0.31
    ారణ
    0.31
     crossorigin
    0.31
    POSITIVE LOGITS
     small
    4.81
    small
    4.72
     SMALL
    4.53
    Small
    4.41
     Small
    4.28
    SMALL
    4.25
     pequeño
    4.16
     pequeña
    4.13
     pequeñas
    4.09
     kecil
    4.06
    Activations Density 1.054%

    No Known Activations