© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4286
    Prev
    Next
    INDEX
    Explanations

    unwanted sexual thoughts

    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_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
     six
    0.37
    '
    0.37
     represented
    0.37
     voic
    0.37
     econometric
    0.37
     Illustrated
    0.37
     lied
    0.37
    ’
    0.37
     illustrated
    0.37
     __
    0.36
    POSITIVE LOGITS
    после
    0.48
    她的
    0.47
    ологии
    0.45
    我们的
    0.44
     ahorita
    0.43
     нашим
    0.41
     spese
    0.41
    фе
    0.41
    ፈላጊ
    0.40
     барои
    0.40
    Activations Density 0.124%

    No Known Activations