© 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. 164592
    Prev
    Next
    INDEX
    Explanations

    calls, labels, authorship

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

    electrostatic force, chemical reactions

    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
    ̣c
    0.48
     cultiv
    0.47
     Fins
    0.46
    に
    0.46
     одновременно
    0.45
     supercritical
    0.45
     preferential
    0.44
     exemption
    0.43
     Grower
    0.42
     ratchet
    0.42
    POSITIVE LOGITS
     cümle
    0.53
    Musical
    0.45
    Thesis
    0.45
    Sin
    0.45
    لب
    0.44
    PHIL
    0.44
     جمل
    0.43
    侮
    0.43
    ব
    0.43
    䢎
    0.43
    Activations Density 0.000%

    No Known Activations