© 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. 7517
    Prev
    Next
    INDEX
    Explanations

    lists, code outputs, and results

    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
     preferably
    0.43
     Preferably
    0.40
    
    0.39
    桠
    0.39
    屣
    0.37
    醅
    0.37
    墀
    0.37
    ፃ
    0.36
    ROLLER
    0.36
    犬
    0.36
    POSITIVE LOGITS
     weird
    0.44
     distorted
    0.43
     ugly
    0.43
    ":
    0.43
     bizarre
    0.42
     hilarious
    0.42
     porque
    0.41
     لأنه
    0.41
     lexic
    0.41
     nicely
    0.40
    Activations Density 0.208%

    No Known Activations