© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-65K
    4. 48690
    Prev
    Next
    INDEX
    Explanations

    greetings and politeness

    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_40_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
     сотрудников
    0.47
    하신
    0.45
    :"))
    0.45
    قافة
    0.44
    ,_-
    0.43
    ."-
    0.43
     用于
    0.43
    ក្រុម
    0.43
     अभिनंदन
    0.42
    ';",
    0.42
    POSITIVE LOGITS
     clim
    0.37
     feel
    0.37
     remember
    0.37
    predicted
    0.36
     ashes
    0.35
     Le
    0.35
     liquef
    0.35
     ავ
    0.35
    Remember
    0.34
     will
    0.34
    Activations Density 0.025%

    No Known Activations