© 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-65K
    7. 28449
    Prev
    Next
    INDEX
    Explanations

    purring, humming, Godwinson, feedback

    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
    hc
    0.45
     motion
    0.44
     hydro
    0.43
    u
    0.43
    ug
    0.42
    eland
    0.41
     hemoglobin
    0.41
    ap
    0.40
     organic
    0.40
     colorless
    0.39
    POSITIVE LOGITS
    Мар
    0.48
     atenção
    0.47
    Cluster
    0.46
    𝚙
    0.46
    尟
    0.46
     competenze
    0.46
     conhecimento
    0.45
    رهای
    0.45
    当我
    0.44
     publicação
    0.44
    Activations Density 0.007%

    No Known Activations