© 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. 6155
    Prev
    Next
    INDEX
    Explanations

    concepts related to possession or relationships

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

    sexualization and exploitation

    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
     walang
    0.41
     The
    0.40
     solche
    0.40
     insgesamt
    0.40
     doet
    0.40
     hlavní
    0.39
     \
    0.39
     fecal
    0.39
     মিলিয়ে
    0.39
     questa
    0.38
    POSITIVE LOGITS
     of
    0.63
    ِ
    0.54
     ofthe
    0.52
    of
    0.45
     thereof
    0.45
    И
    0.45
    sof
    0.45
     của
    0.45
    osphere
    0.44
    ຂອງ
    0.44
    Activations Density 0.168%

    No Known Activations