© 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. 108854
    Prev
    Next
    INDEX
    Explanations

    air, children, geographically, Hydrogen

    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
    н
    0.51
    𒌋
    0.43
     웃
    0.42
    hia
    0.40
    ('--
    0.40
    సూరు
    0.39
    測
    0.39
     быстрее
    0.39
     upped
    0.39
    ни
    0.39
    POSITIVE LOGITS
     dział
    0.53
    WebElement
    0.49
     harus
    0.46
     Swimming
    0.46
     WebElement
    0.45
    扮演
    0.45
     milj
    0.45
    醾
    0.45
     baptism
    0.44
     at
    0.43
    Activations Density 0.017%

    No Known Activations