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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 132884
    Prev
    Next
    INDEX
    Explanations

    age ranges

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

    number ranges with and

    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_262k_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
     حفاظ
    0.46
     nanoparticles
    0.44
     preschoolers
    0.41
    لاميذ
    0.41
    Ϳ
    0.40
    ํานวน
    0.40
     bicyclists
    0.39
     totaling
    0.39
     whirling
    0.39
     microorganisms
    0.38
    POSITIVE LOGITS
    이
    0.45
    e
    0.43
     अपर
    0.42
    스
    0.42
     불러
    0.41
    al
    0.41
     shader
    0.40
     你
    0.40
    ->"
    0.40
     હું
    0.40
    Activations Density 0.002%

    No Known Activations