© 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. 6231
    Prev
    Next
    INDEX
    Explanations

    ethics, credentials, activism, journalism

    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
    자
    0.50
    擴
    0.46
    
    0.44
    تری
    0.44
     расши
    0.43
    보
    0.43
    𝑽
    0.43
    𝗻
    0.42
    이
    0.42
    직
    0.41
    POSITIVE LOGITS
     pathetic
    0.48
     repent
    0.48
     slaying
    0.45
    ayit
    0.44
     back
    0.43
    otive
    0.43
     watery
    0.43
     destroy
    0.42
     mute
    0.42
     peacefully
    0.42
    Activations Density 0.000%

    No Known Activations