© 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. 17757
    Prev
    Next
    INDEX
    Explanations

    identifier or key

    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
    𝘞
    0.43
    ляет
    0.41
    NCc
    0.41
    𝐖
    0.40
    <0x11>
    0.39
    蚌
    0.38
    
    0.38
    ᐋ
    0.38
     mirando
    0.37
    ᴡ
    0.37
    POSITIVE LOGITS
    :
    0.50
     itself
    0.48
     as
    0.44
     herself
    0.39
     ourselves
    0.38
     ===
    0.37
     Turner
    0.36
     Vib
    0.36
     multiply
    0.36
    KeyValue
    0.36
    Activations Density 0.042%

    No Known Activations