© 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. 17524
    Prev
    Next
    INDEX
    Explanations

    markdown link url path separators

    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
    鋳
    0.47
     verste
    0.37
     ∂
    0.37
     inode
    0.36
     bony
    0.36
    ende
    0.36
     penile
    0.35
     palind
    0.34
    seems
    0.34
     nunca
    0.34
    POSITIVE LOGITS
    VOA
    0.45
    潦
    0.43
    骄
    0.41
     Alla
    0.38
    Crisis
    0.38
    },\
    0.38
    .​​
    0.37
    ​​
    0.37
     Crisis
    0.37
    ροσ
    0.37
    Activations Density 0.028%

    No Known Activations