© 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-65K
    7. 63325
    Prev
    Next
    INDEX
    Explanations

    explaining capacity and how

    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_65k_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
    Ин
    0.53
    ро
    0.50
    ূল
    0.50
    オール
    0.49
     chambers
    0.48
    ي
    0.47
    요
    0.47
    ون
    0.46
    داخل
    0.45
    ку
    0.45
    POSITIVE LOGITS
    ibilidad
    0.47
    itt
    0.46
    mäss
    0.46
    ibusdam
    0.46
     Grandpa
    0.44
     Zug
    0.44
     NEP
    0.43
    cach
    0.43
    lyl
    0.43
     τ
    0.42
    Activations Density 0.006%

    No Known Activations