© 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. 48145
    Prev
    Next
    INDEX
    Explanations

    while, whilst

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

    defining replacements

    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
    SearchParams
    0.51
    곱
    0.50
    ﻌ
    0.47
    더
    0.47
    EEP
    0.47
    습
    0.47
    ;
    0.46
    배
    0.46
    거
    0.44
    학년
    0.43
    POSITIVE LOGITS
     كانت
    0.49
     प्रतिनिधित्व
    0.49
     तत्कालीन
    0.46
     জানিয়েছিলেন
    0.46
     акты
    0.45
     বের
    0.45
     відкри
    0.44
     abrió
    0.44
     dibuka
    0.44
     იყო
    0.44
    Activations Density 0.000%

    No Known Activations