© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28772
    Prev
    Next
    INDEX
    Explanations

    Specific booking service

    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
    રમાં
    0.49
     言っ
    0.46
    rictor
    0.43
    ភ្ល
    0.43
    氐
    0.42
    រី
    0.42
     मोहम्मद
    0.41
     মহম্মদ
    0.41
    ancers
    0.41
    érez
    0.40
    POSITIVE LOGITS
    只能
    0.49
    Only
    0.45
     limita
    0.44
     केवल
    0.43
    只
    0.42
    Recipient
    0.42
     밖에
    0.40
     duty
    0.40
     Only
    0.39
    duty
    0.39
    Activations Density 0.002%

    No Known Activations