© 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. 18470
    Prev
    Next
    INDEX
    Explanations

    similar or same

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

    similar items and concepts

    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
    Ü
    0.43
     мини
    0.42
     هر
    0.40
    ΡΙ
    0.40
    ৯
    0.39
    त्‍
    0.39
     ស
    0.37
    ា
    0.37
    тың
    0.37
    ଫ
    0.37
    POSITIVE LOGITS
     similar
    2.25
     similaire
    2.05
    同じ
    1.97
    similar
    1.95
     same
    1.95
    同样的
    1.91
     비슷한
    1.90
     dezelfde
    1.88
     hetzelfde
    1.88
     samme
    1.87
    Activations Density 0.183%

    No Known Activations