© 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. 35684
    Prev
    Next
    INDEX
    Explanations

    even, palindrome

    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
     cocaine
    0.46
     victimization
    0.44
     resistive
    0.43
     tumor
    0.43
    ↵
    0.42
    0.42
     solvents
    0.42
    NCE
    0.41
     troughs
    0.41
     optical
    0.41
    POSITIVE LOGITS
     மட்டும்
    0.48
    烝
    0.48
    会儿
    0.46
    պ
    0.45
    교
    0.45
    இர
    0.44
    嵓
    0.44
    㭂
    0.44
    駋
    0.44
    kamp
    0.44
    Activations Density 0.010%

    No Known Activations