© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83189
    Prev
    Next
    INDEX
    Explanations

    sexualization of violence or trauma

    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
    𝗠
    0.46
     букмекерлик
    0.44
    thisStudent
    0.43
    ahiye
    0.41
    }\|_{
    0.39
     чемпионаты
    0.39
    mith
    0.39
    atedral
    0.39
    allerg
    0.39
    Ⴖ
    0.38
    POSITIVE LOGITS
    ولة
    0.46
     aange
    0.46
    /*
    0.44
     comunicarse
    0.44
     almost
    0.43
     whatever
    0.43
     good
    0.42
     avsl
    0.42
     njegova
    0.42
     sava
    0.42
    Activations Density 0.008%

    No Known Activations