© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51940
    Prev
    Next
    INDEX
    Explanations

    finance and trends

    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
    if
    0.40
    ative
    0.37
    ation
    0.36
        
    0.35
    ere
    0.34
    item
    0.34
    one
    0.34
    ı
    0.34
                
    0.33
    ślin
    0.33
    POSITIVE LOGITS
     signatories
    0.50
     fintech
    0.50
     finan
    0.48
     finance
    0.45
     financ
    0.44
     finans
    0.44
     monetize
    0.44
     financiar
    0.43
     demokrat
    0.41
     citoyens
    0.41
    Activations Density 0.000%

    No Known Activations