© 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. 145821
    Prev
    Next
    INDEX
    Explanations

    visit your

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

    foreign/unfamiliar words, elections, commerce

    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
     पंडित
    0.51
    ToPointer
    0.51
    ﻉ
    0.50
     завжди
    0.50
     ദേശ
    0.50
     sempre
    0.49
     జ్ఞ
    0.49
    stev
    0.49
     เดิม
    0.48
     จุด
    0.47
    POSITIVE LOGITS
     candidacy
    0.49
    \
    0.49
     candidates
    0.46
    carbox
    0.46
     fodder
    0.44
     quicker
    0.43
    opathy
    0.43
    ');
    0.42
     cheaper
    0.42
     lashes
    0.42
    Activations Density 0.001%

    No Known Activations