© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1900
    Prev
    Next
    INDEX
    Explanations

    family

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

    family

    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
    orption
    0.37
     হাইড্র
    0.35
    暧
    0.35
     uncorrelated
    0.34
     Electrons
    0.34
    নীতির
    0.33
    ᵘ
    0.33
    ^{+
    0.32
    rotic
    0.32
     skimage
    0.32
    POSITIVE LOGITS
     family
    4.97
    family
    4.75
    家族
    4.50
     família
    4.38
     FAMILY
    4.38
     가족
    4.38
    Family
    4.34
     familie
    4.34
     خانواده
    4.34
     familia
    4.28
    Activations Density 0.786%

    No Known Activations