© 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. 175463
    Prev
    Next
    INDEX
    Explanations

    regular college application

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

    record, likelihood, spot, nights

    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
    nd
    0.59
    s
    0.52
    bc
    0.47
    zler
    0.47
     weeping
    0.47
     brunes
    0.46
     cs
    0.46
     thinking
    0.46
    alanx
    0.46
     globules
    0.46
    POSITIVE LOGITS
    Ша
    0.53
    隱
    0.53
    다라고
    0.51
    崗
    0.49
    輸
    0.48
     Университе
    0.47
    δο
    0.46
    壇
    0.46
    щал
    0.46
    禿
    0.46
    Activations Density 0.001%

    No Known Activations