© 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. 236407
    Prev
    Next
    INDEX
    Explanations

    addressing you

    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
    ๊
    0.45
    ार्मिक
    0.42
     verb
    0.42
    Verb
    0.40
    ্ব
    0.40
     boiler
    0.39
    र्म
    0.39
     вики
    0.39
    ੋ
    0.39
     harmon
    0.38
    POSITIVE LOGITS
     તેમને
    0.47
    angga
    0.45
     کمپیوٹر
    0.45
     તેમણે
    0.44
    នៃការ
    0.44
     Tanah
    0.41
    ENGE
    0.41
     پیسې
    0.41
     sentencia
    0.41
     Frum
    0.41
    Activations Density 0.009%

    No Known Activations