© 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. 17017
    Prev
    Next
    INDEX
    Explanations

    count followed by less, me, number, inuous, on, able

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

    counting numbers and items

    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
    macht
    0.44
    amplitude
    0.43
     constantes
    0.43
    athar
    0.41
     वाट
    0.40
     आहोत
    0.39
     моз
    0.38
    酵
    0.38
     दिली
    0.38
     Такой
    0.38
    POSITIVE LOGITS
    DownLatch
    1.17
    inue
    0.94
    enance
    0.90
    inuous
    0.82
    Vectorizer
    0.72
    inued
    0.71
    rified
    0.68
    (*)
    0.67
    downs
    0.62
     zählen
    0.60
    Activations Density 0.024%

    No Known Activations