© 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. 152001
    Prev
    Next
    INDEX
    Explanations

    off and profit discounts

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

    enthusiastically, feeling, professional, steel

    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
    یا
    0.49
    યુ
    0.48
     Hut
    0.47
    خصوص
    0.45
    foy
    0.45
    w
    0.45
     તે
    0.43
    vz
    0.43
    c
    0.43
    world
    0.42
    POSITIVE LOGITS
     konflikt
    0.51
    insk
    0.46
    ăl
    0.46
     sektor
    0.46
     janela
    0.46
    тости
    0.45
     permasalahan
    0.45
     konkret
    0.44
    тое
    0.44
     påver
    0.44
    Activations Density 0.001%

    No Known Activations