© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 205795
    Prev
    Next
    INDEX
    Explanations

    specific qualities or actions

    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_40_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
     MAN
    0.43
     manual
    0.42
     ton
    0.41
    cubic
    0.41
     ¾
    0.39
    inline
    0.39
     multif
    0.38
     tons
    0.37
     Ton
    0.37
    शीलता
    0.37
    POSITIVE LOGITS
    访
    0.42
    睒
    0.42
    ᆫ
    0.41
    ಐ
    0.40
    Джо
    0.40
    ונ
    0.38
     occuper
    0.38
    詆
    0.38
     Сти
    0.38
    NB
    0.37
    Activations Density 0.001%

    No Known Activations