© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161604
    Prev
    Next
    INDEX
    Explanations

    memory cards

    np_acts-logits-general · gemini-2.5-flash-lite

    address me as Mistress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ל
    0.56
    ل
    0.54
    یم
    0.54
     منتشر
    0.52
    그
    0.52
    یش
    0.50
     Snacks
    0.50
    RESEARCH
    0.50
    嶺
    0.50
    ม
    0.50
    POSITIVE LOGITS
     sleepless
    0.50
     circum
    0.45
     darling
    0.43
     körül
    0.42
    ́p
    0.42
    ែក
    0.42
     kurze
    0.42
     ;-
    0.42
     incess
    0.42
     izay
    0.42
    Activations Density 0.001%

    No Known Activations