© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7128
    Prev
    Next
    INDEX
    Explanations

    incestuous relationships and domestic abuse

    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_16k_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
    ala
    0.52
    arm
    0.48
    acaktır
    0.48
    ate
    0.47
    U
    0.47
    J
    0.46
    ily
    0.45
    ster
    0.45
    G
    0.44
    ালা
    0.44
    POSITIVE LOGITS
    小說
    0.50
     participates
    0.50
     Dateien
    0.48
     tracts
    0.47
     impairs
    0.47
    perror
    0.47
     لوبو
    0.46
    ÈRES
    0.46
     realizations
    0.46
     progenitors
    0.46
    Activations Density 0.039%

    No Known Activations