© 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. 24092
    Prev
    Next
    INDEX
    Explanations

    conceptual representations

    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
     mundur
    0.52
    اسی
    0.51
    etzten
    0.49
    의
    0.48
    ای
    0.47
     রীতি
    0.45
    口气
    0.44
    ार्किक
    0.44
    ख
    0.44
    長さ
    0.43
    POSITIVE LOGITS
    TextAlign
    0.51
     формирование
    0.46
     只
    0.45
    ᄅ
    0.43
    воды
    0.43
    𝙩
    0.43
     $("
    0.42
     に対
    0.41
     保護
    0.41
     యా
    0.41
    Activations Density 0.001%

    No Known Activations