© 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. 83928
    Prev
    Next
    INDEX
    Explanations

    public constructors in code

    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
    asy
    0.43
    obiles
    0.42
    䢌
    0.41
    run
    0.39
    private
    0.38
    ത്തിലേ
    0.38
     мыкты
    0.37
    шку
    0.37
    yong
    0.37
     את
    0.36
    POSITIVE LOGITS
     forme
    0.37
    ংশ
    0.36
    ɴ
    0.36
    itioners
    0.35
    何の
    0.35
    瑟
    0.34
     bri
    0.34
    出生
    0.34
    nonpayable
    0.33
    uator
    0.32
    Activations Density 0.012%

    No Known Activations