© 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. 56005
    Prev
    Next
    INDEX
    Explanations

    classifications and interactions

    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
    擬
    0.46
    aszt
    0.46
     rejoindre
    0.45
     particulier
    0.44
    жливо
    0.44
    𝚓
    0.44
    engagement
    0.42
     instância
    0.42
     descansar
    0.42
    一
    0.41
    POSITIVE LOGITS
    CCH
    0.49
     e
    0.46
     tasty
    0.43
     реаль
    0.43
     economics
    0.43
     Q
    0.42
     V
    0.42
     Z
    0.42
    Ge
    0.42
     Lead
    0.42
    Activations Density 0.009%

    No Known Activations