© 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. 79884
    Prev
    Next
    INDEX
    Explanations

    existential risk, overdose, hair, euthanasia

    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
    >∕</
    0.46
     flowering
    0.45
    眼神
    0.45
    ي
    0.45
     lifelong
    0.45
     असंभव
    0.45
    ి
    0.44
    蚩
    0.43
     proliferative
    0.42
     affording
    0.42
    POSITIVE LOGITS
    adisu
    0.49
    asang
    0.46
     рассказать
    0.45
     sedangkan
    0.44
    ósito
    0.44
     असताना
    0.44
     Ethiopia
    0.44
     rupiah
    0.44
     alak
    0.42
     있었다
    0.42
    Activations Density 0.002%

    No Known Activations