© 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-262K
    7. 71074
    Prev
    Next
    INDEX
    Explanations

    fear, worry, death, murder

    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
    嘜
    0.50
    𝙋
    0.49
    𝙥
    0.48
    ଗ
    0.47
     instytuc
    0.47
     undangan
    0.45
     इम्यूनिटी
    0.45
     operativo
    0.45
    ими
    0.45
     faaliyet
    0.44
    POSITIVE LOGITS
     I
    0.50
     Death
    0.44
     he
    0.42
     Peace
    0.41
     Blood
    0.40
     Use
    0.40
     Xi
    0.39
     Vietnam
    0.39
     Erin
    0.39
     Victims
    0.38
    Activations Density 0.001%

    No Known Activations