© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 227579
    Prev
    Next
    INDEX
    Explanations

    additional fee

    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
    覚
    0.53
    บัติ
    0.51
    сіб
    0.51
    ืน
    0.50
    墘
    0.50
     устройства
    0.49
    Devices
    0.46
     устройств
    0.46
    Meesho
    0.46
    覚え
    0.45
    POSITIVE LOGITS
     translator
    0.54
     piden
    0.50
    un
    0.48
    ois
    0.47
    usd
    0.46
     hospital
    0.45
     price
    0.45
     translation
    0.44
    o
    0.43
    et
    0.43
    Activations Density 0.001%

    No Known Activations