© 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. 224412
    Prev
    Next
    INDEX
    Explanations

    house and closure

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

    medical and scientific terms

    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
    ...\...\
    0.52
     certific
    0.50
    ➎
    0.46
    ..
    0.45
     repository
    0.45
     samtid
    0.45
     doctorate
    0.44
     archaeologist
    0.44
     cultiv
    0.44
     certificate
    0.44
    POSITIVE LOGITS
    ைகோ
    0.55
    רו
    0.51
     ਬ
    0.49
    Τα
    0.49
    𝐒
    0.48
    樓
    0.48
    ovať
    0.48
    洛
    0.47
    國際
    0.46
    ंकिंग
    0.46
    Activations Density 0.000%

    No Known Activations