© 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. 12251
    Prev
    Next
    INDEX
    Explanations

    gmail addresses and github websites

    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
    IB
    0.46
    ρά
    0.44
    lád
    0.43
    Cox
    0.42
    ן
    0.42
    வுகளில்
    0.41
    ते
    0.41
    8
    0.40
    <0xA1>
    0.40
    bill
    0.40
    POSITIVE LOGITS
     Gmail
    0.51
     Trat
    0.46
     offre
    0.46
     abre
    0.45
     bson
    0.45
     Botox
    0.45
     Một
    0.44
     Scenario
    0.44
     romanzo
    0.43
     Qualquer
    0.43
    Activations Density 0.002%

    No Known Activations