© 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-262K
    7. 79764
    Prev
    Next
    INDEX
    Explanations

    sexual exploitation and humiliation

    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_262k_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
    工艺
    0.41
    设计
    0.41
    适用于
    0.40
     Когда
    0.40
    被称为
    0.39
    倬
    0.38
     Specifically
    0.38
    П
    0.38
     опера
    0.37
     பொதுவாக
    0.37
    POSITIVE LOGITS
     humiliated
    0.63
     humiliation
    0.59
     humiliating
    0.59
     disgraceful
    0.58
     injustices
    0.53
     sufferings
    0.52
     humili
    0.52
     disappointments
    0.52
     miserable
    0.49
     shameful
    0.49
    Activations Density 0.002%

    No Known Activations