© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78191
    Prev
    Next
    INDEX
    Explanations

    programming, technical, data, verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    to
    0.52
    砸
    0.49
     similar
    0.49
    similar
    0.49
     similaire
    0.48
    ਵ
    0.46
    ਰ
    0.46
    ਜ਼
    0.46
    ﻑ
    0.46
    causing
    0.46
    POSITIVE LOGITS
     Ascent
    0.58
     elf
    0.50
     Bez
    0.47
     ascent
    0.45
     Kemp
    0.44
     opt
    0.44
     Oculus
    0.44
     Industria
    0.44
     Autodesk
    0.44
     Heng
    0.43
    Activations Density 0.000%

    No Known Activations