© 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. 36295
    Prev
    Next
    INDEX
    Explanations

    negative differences and calculations

    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
     Traffic
    0.46
     tinggi
    0.45
     higher
    0.44
     Summer
    0.44
     Relay
    0.43
     Higher
    0.43
    ຈັດສົ່ງ
    0.43
    桕
    0.41
    Festival
    0.41
    high
    0.40
    POSITIVE LOGITS
     negative
    1.41
    Negative
    1.27
     negatif
    1.26
     negativos
    1.26
    negative
    1.25
     negativo
    1.24
     Negative
    1.22
     negativity
    1.21
     negat
    1.20
     negativ
    1.13
    Activations Density 0.342%

    No Known Activations