© 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. 12168
    Prev
    Next
    INDEX
    Explanations

    Angular OnInit

    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
     अकादमी
    0.42
    *
    0.41
    🥇
    0.40
    Descriptions
    0.40
    
    0.40
    的用户
    0.40
    组成的
    0.40
    冦
    0.39
    *.
    0.38
    🐛
    0.38
    POSITIVE LOGITS
    become
    0.41
     Adler
    0.40
     SEE
    0.39
     ontological
    0.39
     경우
    0.39
     bli
    0.39
    сторі
    0.39
     కు
    0.38
    embr
    0.38
     Become
    0.38
    Activations Density 0.011%

    No Known Activations