© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2747
    Prev
    Next
    INDEX
    Explanations

    unethical content concerns

    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_16_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
     it
    0.84
    Про
    0.80
    ക
    0.80
    O
    0.79
    ปัญหา
    0.78
    При
    0.76
    К
    0.75
    お
    0.75
    म
    0.75
    τη
    0.74
    POSITIVE LOGITS
    ни
    0.92
    s
    0.92
    ac
    0.91
    n
    0.88
    -
    0.86
    ari
    0.84
    y
    0.83
    el
    0.80
    .
    0.80
    ↵
    0.80
    Activations Density 0.396%

    No Known Activations