© 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. 55754
    Prev
    Next
    INDEX
    Explanations

    conjunctions and contrast across languages

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

    challenge or impossibility

    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
    とのこと
    0.45
    DOF
    0.44
    ር
    0.44
    株式会社
    0.42
    Stroke
    0.41
    Leaves
    0.41
    g
    0.41
    port
    0.40
    s
    0.40
    会社
    0.39
    POSITIVE LOGITS
     nhưng
    0.62
     mutta
    0.55
     یا
    0.54
     lakini
    0.52
     Nhưng
    0.50
     ataupun
    0.50
    但是在
    0.49
    但是我
    0.49
     but
    0.49
     eğer
    0.48
    Activations Density 0.000%

    No Known Activations