© 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-65K
    4. 47993
    Prev
    Next
    INDEX
    Explanations

    words starting analysis or introductions

    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_65k_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
     Whitt
    0.47
     isn
    0.47
    气候
    0.47
     Whittier
    0.46
     मालिक
    0.45
     đủ
    0.45
    >∈</
    0.44
    椇
    0.44
    ./
    0.43
     suble
    0.43
    POSITIVE LOGITS
    رمز
    0.47
     bonheur
    0.46
    ッと
    0.45
     sketchy
    0.44
     dodgy
    0.43
    lingu
    0.42
    ur
    0.42
    රු
    0.42
    کس
    0.41
     grungy
    0.41
    Activations Density 0.001%

    No Known Activations