© 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. 40-GEMMASCOPE-2-RES-262K
    7. 607
    Prev
    Next
    INDEX
    Explanations

    package manager commands

    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
    饵
    0.46
     അമ്മ
    0.44
    餞
    0.41
    桿
    0.40
    Humidity
    0.40
    ᓃ
    0.40
     جوړونک
    0.39
    多家
    0.39
     Epstein
    0.39
    Liability
    0.39
    POSITIVE LOGITS
     --
    0.68
     -
    0.62
    ctl
    0.54
    manage
    0.51
    --
    0.48
     manage
    0.47
     get
    0.47
    cli
    0.46
     inspect
    0.46
     freeze
    0.45
    Activations Density 0.041%

    No Known Activations