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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11809
    Prev
    Next
    INDEX
    Explanations

    expenses, taxes, operating costs

    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
     rejoindre
    0.49
    渔
    0.46
     diminta
    0.44
     vara
    0.43
     bú
    0.41
     berbah
    0.40
     cherche
    0.40
     Lingu
    0.40
     squadra
    0.40
    雞
    0.39
    POSITIVE LOGITS
    ME
    0.42
     ప్రపంచ
    0.40
    CORDS
    0.39
    INR
    0.39
     topics
    0.39
    meV
    0.38
    माइंडर
    0.38
    ICAGO
    0.38
    ಿಯಾಗ
    0.37
     സെക്ര
    0.37
    Activations Density 0.000%

    No Known Activations