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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 224272
    Prev
    Next
    INDEX
    Explanations

    how to build relationships

    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
     বক্তব্যের
    0.42
     Lovers
    0.41
     queer
    0.41
    Sex
    0.41
     घना
    0.38
     Scenes
    0.38
     Queer
    0.38
    ฮ
    0.38
    썩
    0.38
     sexually
    0.38
    POSITIVE LOGITS
    海外
    0.48
     അവളെ
    0.47
     सफलता
    0.46
     repatri
    0.46
     viajar
    0.46
     travelling
    0.45
     سفر
    0.45
     importation
    0.45
     encont
    0.44
     overseas
    0.44
    Activations Density 0.006%

    No Known Activations