© 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. 218585
    Prev
    Next
    INDEX
    Explanations

    quantities, questions, quality, sequence

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

    explosions and loss of limbs

    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
    createQuery
    0.44
     celebrating
    0.39
     Cemetery
    0.39
     nati
    0.39
    Petra
    0.39
     অন্ত
    0.38
    傥
    0.38
    麒
    0.38
     Petra
    0.37
    赛事
    0.37
    POSITIVE LOGITS
     yellowish
    0.44
    propan
    0.40
     lesions
    0.39
     GLASS
    0.39
     IEEE
    0.39
     ガラス
    0.39
    WH
    0.38
     gloves
    0.38
    TABLE
    0.37
    相對
    0.37
    Activations Density 0.003%

    No Known Activations