© 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. 40-GEMMASCOPE-2-RES-262K
    7. 135514
    Prev
    Next
    INDEX
    Explanations

    sexual fantasies, daydreams

    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_40_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
    azir
    0.45
    ظيم
    0.44
    挑戰
    0.43
    䐍
    0.42
     firef
    0.42
    ázky
    0.41
    𝗪
    0.41
    ских
    0.40
    ಗಿ
    0.40
    馭
    0.40
    POSITIVE LOGITS
     Ancest
    0.43
     humbly
    0.40
     بخشی
    0.38
    ینو
    0.37
     yazı
    0.37
     rejo
    0.36
     researcher
    0.36
     Encyclopedia
    0.36
     ancestral
    0.36
     겸
    0.36
    Activations Density 0.004%

    No Known Activations