© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17163
    Prev
    Next
    INDEX
    Explanations

    actual real compatible images PET primary

    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
    Omega
    0.51
    Quarter
    0.47
     ква
    0.47
    ☇
    0.47
    कने
    0.44
    ﹉
    0.43
    来自于
    0.43
    オート
    0.43
    никова
    0.43
    Attributes
    0.42
    POSITIVE LOGITS
     clade
    0.54
     Leningrad
    0.49
    ,}
    0.47
     armon
    0.47
     classe
    0.46
    ט
    0.45
    шен
    0.45
    нг
    0.44
    ต์
    0.44
     Teile
    0.44
    Activations Density 0.000%

    No Known Activations