© 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. 55224
    Prev
    Next
    INDEX
    Explanations

    accrued interest

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

    directly manipulate color or disc material

    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
    Olivia
    0.51
    Deborah
    0.45
    Emily
    0.45
    Rebecca
    0.44
    Apple
    0.44
    发布
    0.43
    Didn
    0.43
     ":"
    0.43
    Did
    0.42
    ण्ड
    0.42
    POSITIVE LOGITS
    passenger
    0.47
    ेंटीना
    0.47
    伎
    0.47
    ্ী
    0.46
     executes
    0.46
    anch
    0.46
    riel
    0.45
    ẵ
    0.45
     أح
    0.44
    insa
    0.44
    Activations Density 0.000%

    No Known Activations