© 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. 168206
    Prev
    Next
    INDEX
    Explanations

    for board presence were of are can Keep straight

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

    download model weights

    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
    are
    0.44
    on
    0.43
    ous
    0.42
     railroads
    0.42
    U
    0.42
     Accompl
    0.41
    mel
    0.41
     services
    0.41
    య
    0.39
     platforms
    0.39
    POSITIVE LOGITS
     Verhalten
    0.48
     Unterschiede
    0.47
     Sunak
    0.46
    рифмети
    0.46
     Oxfordshire
    0.45
    以降
    0.45
     során
    0.45
     underwhelming
    0.45
     StandardScaler
    0.45
     фізи
    0.45
    Activations Density 0.001%

    No Known Activations