© 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. 31-GEMMASCOPE-2-RES-16K
    7. 16356
    Prev
    Next
    INDEX
    Explanations

    low frequency or small quantities

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

    unusual or rare things

    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_31_width_16k_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
     여러
    0.46
     almeno
    0.44
    꿰
    0.44
     tonnes
    0.44
    หลาย
    0.44
    Unnamed
    0.44
     cheerfully
    0.43
     somew
    0.42
    เ
    0.42
     상관
    0.42
    POSITIVE LOGITS
    很少
    1.33
    寥
    1.27
     rarely
    1.20
     wenigen
    1.20
     meagre
    1.18
     seldom
    1.14
     meager
    1.13
     selten
    1.11
     few
    1.09
     rare
    1.09
    Activations Density 0.748%

    No Known Activations