© 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. 5694
    Prev
    Next
    INDEX
    Explanations

    single followed by other words

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

    single word or point

    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
    埧
    0.41
     particolari
    0.40
    ainte
    0.39
    adanam
    0.39
    omata
    0.38
    ove
    0.38
    onance
    0.38
    𝙜
    0.37
     সিরিজ
    0.37
     extravaganza
    0.37
    POSITIVE LOGITS
     single
    1.16
    handedly
    1.13
    single
    1.11
     solitary
    1.06
     Single
    1.05
     SINGLE
    1.02
    Single
    1.02
    单
    1.00
    tons
    0.93
     एकल
    0.93
    Activations Density 0.045%

    No Known Activations