© 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. 61048
    Prev
    Next
    INDEX
    Explanations

    campaign series

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

    analytical, physical, safety, consulting

    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
    плуа
    0.50
     दशहरा
    0.47
     옳은
    0.46
     NextResponse
    0.44
    饰
    0.42
    ත්මක
    0.42
    軀
    0.42
     esterno
    0.41
    думы
    0.41
     प्रूव
    0.41
    POSITIVE LOGITS
    ﺶ
    0.51
    jung
    0.49
    landing
    0.46
     monstros
    0.46
    i
    0.45
    ﺪ
    0.45
    helium
    0.45
    serie
    0.45
    ﻄ
    0.45
    pagination
    0.44
    Activations Density 0.000%

    No Known Activations