© 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. 31-GEMMASCOPE-2-RES-262K
    4. 53725
    Prev
    Next
    INDEX
    Explanations

    Australian history and sports

    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
     emphasise
    0.41
    താ
    0.40
     continental
    0.39
     elevationMap
    0.38
    以内に
    0.37
    ৳
    0.37
    バリ
    0.36
     Whisky
    0.36
    getJSON
    0.36
    fjord
    0.36
    POSITIVE LOGITS
     AFL
    0.47
     progen
    0.41
    &=
    0.40
    ática
    0.40
     Dodgers
    0.39
    ці
    0.39
    િટ
    0.38
    女友
    0.38
     NFL
    0.38
    𝓼
    0.38
    Activations Density 0.011%

    No Known Activations